Triton server died before reaching ready state. Terminating Riva startup

AI & Data Science Deep Learning (Training & Inference) Riva
#1

Please provide the following information when requesting support.

Hardware - GPU (A100)
Hardware - CPU
Operating System: Ubuntu 20.04
Riva Version: 1.6.0-beta
TLT Version

Hi

I would like to test Riva on the workstation, since there is no internet access on this workstation, here is what I’ve done:

  1. Download the docker images to my Linux device via running bash riva_init.sh
  2. Save these 3 docker images into tar.gz file
  3. Transfer those 3 tar.gz files to the workstation.
  4. Load docker images with these 3 tar.gz files on the workstation
  5. Run bash riva_start.sh on the workstation

then I got an error

Triton server died before reaching ready state. Terminating Riva startup.

here is the complete log message:

==========================
=== Riva Speech Skills ===

NVIDIA Release 21.09 (build 27567456)

Copyright (c) 2018-2021, NVIDIA CORPORATION. All rights reserved.

Various files include modifications (c) NVIDIA CORPORATION. All rights reserved.
NVIDIA modifications are covered by the license terms that apply to the underlying
project or file.

Riva waiting for Triton server to load all models…retrying in 1 second
I1007 07:32:54.182862 70 metrics.cc:228] Collecting metrics for GPU 0: NVIDIA A100-SXM-80GB
I1007 07:32:54.183331 70 tritonserver.cc:1658]
±---------------------------------±---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Option | Value |
±---------------------------------±---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| server_id | triton |
| server_version | 2.9.0 |
| server_extensions | classification sequence model_repository model_repository(unload_dependents) schedule_policy model_configuration system_shared_memory cuda_shared_memory binary_tensor_data statistics |
| model_control_mode | MODE_NONE |
| strict_model_config | 1 |
| pinned_memory_pool_byte_size | 268435456 |
| cuda_memory_pool_byte_size{0} | 1000000000 |
| min_supported_compute_capability | 6.0 |
| strict_readiness | 1 |
| exit_timeout | 30 |
±---------------------------------±---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

I1007 07:32:54.183346 70 server.cc:231] No server context available. Exiting immediately.
error: creating server: Invalid argument - --model-repository must be specified

Riva waiting for Triton server to load all models…retrying in 1 second
Riva waiting for Triton server to load all models…retrying in 1 second
Triton server died before reaching ready state. Terminating Riva startup.
Check Triton logs with: docker logs
/opt/riva/bin/start-riva: line 1: kill: (70) - No such process

1 Like
Triton server died before reaching ready state. Terminating Riva startup
#2

Hi,

Looks like your Triton server is down, due to models are not loaded using --model-repository option. Could you please share us docker log and config file/steps to understand the deployment here for better help.

Thank you.

#3

Hi spolisetty
The log message that I provided earlier is the one that I get via running docker logs riva-speech

Here is the content of config.sh that is under folder riva_quickstart_v1.6.0-beta

# Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.

#

# NVIDIA CORPORATION and its licensors retain all intellectual property

# and proprietary rights in and to this software, related documentation

# and any modifications thereto. Any use, reproduction, disclosure or

# distribution of this software and related documentation without an express

# license agreement from NVIDIA CORPORATION is strictly prohibited.

# Enable or Disable Riva Services

service_enabled_asr=true

service_enabled_nlp=true

service_enabled_tts=true

# Specify one or more GPUs to use

# specifying more than one GPU is currently an experimental feature, and may result in undefined behaviours.

gpus_to_use="device=0"

# Specify the encryption key to use to deploy models

MODEL_DEPLOY_KEY="tlt_encode"

# Locations to use for storing models artifacts

#

# If an absolute path is specified, the data will be written to that location

# Otherwise, a docker volume will be used (default).

#

# riva_init.sh will create a `rmir` and `models` directory in the volume or

# path specified.

#

# RMIR ($riva_model_loc/rmir)

# Riva uses an intermediate representation (RMIR) for models

# that are ready to deploy but not yet fully optimized for deployment. Pretrained

# versions can be obtained from NGC (by specifying NGC models below) and will be

# downloaded to $riva_model_loc/rmir by `riva_init.sh`

#

# Custom models produced by NeMo or TLT and prepared using riva-build

# may also be copied manually to this location $(riva_model_loc/rmir).

#

# Models ($riva_model_loc/models)

# During the riva_init process, the RMIR files in $riva_model_loc/rmir

# are inspected and optimized for deployment. The optimized versions are

# stored in $riva_model_loc/models. The riva server exclusively uses these

# optimized versions.

riva_model_loc="riva-model-repo"

# The default RMIRs are downloaded from NGC by default in the above $riva_rmir_loc directory

# If you'd like to skip the download from NGC and use the existing RMIRs in the $riva_rmir_loc

# then set the below $use_existing_rmirs flag to true. You can also deploy your set of custom

# RMIRs by keeping them in the riva_rmir_loc dir and use this quickstart script with the

# below flag to deploy them all together.

use_existing_rmirs=false

# Ports to expose for Riva services

riva_speech_api_port="50051"

riva_vision_api_port="60051"

# NGC orgs

riva_ngc_org="nvidia"

riva_ngc_team="riva"

riva_ngc_image_version="1.6.0-beta"

riva_ngc_model_version="1.6.0-beta"

# Pre-built models listed below will be downloaded from NGC. If models already exist in $riva-rmir

# then models can be commented out to skip download from NGC

########## ASR MODELS ##########

models_asr=(

### Punctuation model

"${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_punctuation_bert_base:${riva_ngc_model_version}"

### Citrinet-1024 Streaming w/ CPU decoder, best latency configuration

"${riva_ngc_org}/${riva_ngc_team}/rmir_asr_citrinet_1024_asrset3p0_streaming:${riva_ngc_model_version}"

### Citrinet-1024 Streaming w/ CPU decoder, best throughput configuration

# "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_citrinet_1024_asrset3p0_streaming_throughput:${riva_ngc_model_version}"

### Citrinet-1024 Offline w/ CPU decoder,

"${riva_ngc_org}/${riva_ngc_team}/rmir_asr_citrinet_1024_asrset3p0_offline:${riva_ngc_model_version}"

### Jasper Streaming w/ CPU decoder, best latency configuration

# "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_english_streaming:${riva_ngc_model_version}"

### Jasper Streaming w/ CPU decoder, best throughput configuration

# "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_english_streaming_throughput:${riva_ngc_model_version}"

### Jasper Offline w/ CPU decoder

# "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_english_offline:${riva_ngc_model_version}"

### Quarztnet Streaming w/ CPU decoder, best latency configuration

# "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_quartznet_english_streaming:${riva_ngc_model_version}"

### Quarztnet Streaming w/ CPU decoder, best throughput configuration

# "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_quartznet_english_streaming_throughput:${riva_ngc_model_version}"

### Quarztnet Offline w/ CPU decoder

# "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_quartznet_english_offline:${riva_ngc_model_version}"

### Jasper Streaming w/ GPU decoder, best latency configuration

# "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_english_streaming_gpu_decoder:${riva_ngc_model_version}"

### Jasper Streaming w/ GPU decoder, best throughput configuration

# "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_english_streaming_throughput_gpu_decoder:${riva_ngc_model_version}"

### Jasper Offline w/ GPU decoder

# "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_english_offline_gpu_decoder:${riva_ngc_model_version}"

)

########## NLP MODELS ##########

models_nlp=(

### Bert base Punctuation model

"${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_punctuation_bert_base:${riva_ngc_model_version}"

### BERT base Named Entity Recognition model fine-tuned on GMB dataset with class labels LOC, PER, ORG etc.

"${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_named_entity_recognition_bert_base:${riva_ngc_model_version}"

### BERT Base Intent Slot model fine-tuned on weather dataset.

"${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_intent_slot_bert_base:${riva_ngc_model_version}"

### BERT Base Question Answering model fine-tuned on Squad v2.

"${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_question_answering_bert_base:${riva_ngc_model_version}"

### Megatron345M Question Answering model fine-tuned on Squad v2.

# "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_question_answering_megatron:${riva_ngc_model_version}"

### Bert base Text Classification model fine-tuned on 4class (weather, meteorology, personality, nomatch) domain model.

"${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_text_classification_bert_base:${riva_ngc_model_version}"

)

########## TTS MODELS ##########

models_tts=(

"${riva_ngc_org}/${riva_ngc_team}/rmir_tts_fastpitch_hifigan_ljspeech:${riva_ngc_model_version}"

# "${riva_ngc_org}/${riva_ngc_team}/rmir_tts_tacotron_waveglow_ljspeech:${riva_ngc_model_version}"

)

NGC_TARGET=${riva_ngc_org}

if [[ ! -z ${riva_ngc_team} ]]; then

NGC_TARGET="${NGC_TARGET}/${riva_ngc_team}"

else

team="\"\""

fi

# define docker images required to run Riva

image_client="nvcr.io/${NGC_TARGET}/riva-speech-client:${riva_ngc_image_version}"

image_speech_api="nvcr.io/${NGC_TARGET}/riva-speech:${riva_ngc_image_version}-server"

# define docker images required to setup Riva

image_init_speech="nvcr.io/${NGC_TARGET}/riva-speech:${riva_ngc_image_version}-servicemaker"

# daemon names

riva_daemon_speech="riva-speech"

riva_daemon_client="riva-client"
#4

BTW, here is the log while running bash riva_start.sh

$ bash riva_start.sh
Starting Riva Speech Services. This may take several minutes depending on the number of models deployed.
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Health ready check failed.
Check Riva logs with: docker logs riva-speech
$ docker logs riva-speech
#5

and…here is another log while running bash riva_init.sh on my edge device (not workstation)

Downloading models (RMIRs) from NGC...
Note: this may take some time, depending on the speed of your Internet connection.
To skip this process and use existing RMIRs set the location and corresponding flag in config.sh.
WARNING: The requested image's platform (linux/amd64) does not match the detected host platform (linux/arm64/v8) and no specific platform was requested
docker: Error response from daemon: OCI runtime create failed: container_linux.go:380: starting container process caused: process_linux.go:545: container init caused: Running hook #0:: error running hook: exit status 1, stdout: , stderr: exec command: [/usr/bin/nvidia-container-cli --load-kmods configure --ldconfig=@/sbin/ldconfig.real --device=0 --compute --utility --video --require=cuda>=9.0 --pid=17492 /var/lib/docker/overlay2/7c69fdb7e53829db6a69d720d32ea7b28ab6a0f74b9174bcd1e8e49639f90b85/merged]
nvidia-container-cli: mount error: mount operation failed: /usr/src/tensorrt: no such file or directory: unknown.
Error in downloading models.
#6

Hi,

Could you please let us know edge device are you using here. Just for your info please make sure, you’re using supported hardware. Please refer support matrix here Support Matrix — NVIDIA Riva
For your reference similar error,
Failed to run tensorrt docker image on Jetson Nano - #3 by AastaLLL

Thank you.

#7

Hi
the edge device that I used is Jetson Nano.
I know that Jetson is not a supported hardware for Riva, so I just use it to download docker images from NGC via running riva_init.sh.
Once the images are downloaded, I transfer them to workstation, where I plan to run Riva. (p.s. There is no internet access on Workstation).

It seems that the models (RMIRs) are planned to be downloaded from NGC when running riva_init.sh, is there any way that I could skip the model downloading process?

And how could I download this models not via running riva_init.sh?

#8

Hi,

Sorry for the delayed response. We can either comment out all the models or set all the service enabled flags to false. All of the models enumerated in config.sh correspond to paths in NGC. We can use the NGC CLI to download them manually.

Thank you.

#9

Hi
Thanks for your reply, I have set all the service enable flags to false and use_existing_rmirs to true. I also comment out the portion of checking NGC API key in riva_init.sh, here I attached my new config.sh and riva_init.sh

However, I still cannot initialize Riva properly due to the following error after running riva_init.sh

find: '/data/rmir': No sush file or directly

It came from the last docker command in riva_init.sh

docker run --init -it --rm --gpus '"'$gpus_to_use'"' \
  -v $riva_model_loc:/data \
  -e "MODEL_DEPLOY_KEY=${MODEL_DEPLOY_KEY}" \
          --name riva-service-maker \
  $image_init_speech deploy_all_models /data/rmir /data/models

Here are my questions:

  1. Where should I create the folder $riva_model_loc? Is it under riva_quickstart_v1.6.0-beta?
  2. Should I download the models first before running riva_init.sh?
  3. Where could I find theses models on NGC? (i.e. I see "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_punctuation_bert_base:${riva_ngc_model_version}") in the config.sh as one of the ASR models, how could I find it on NGC? Querying “Punctuation model” gives me too many results and I have no way to filter further

image
image1920×1080 368 KB

  1. and where should I store these models locally? Should I keep them in the folder $riva_model_loc/rmir ?

Config.sh

# Copyright (c) 2021, NVIDIA CORPORATION.  All rights reserved.
#
# NVIDIA CORPORATION and its licensors retain all intellectual property
# and proprietary rights in and to this software, related documentation
# and any modifications thereto.  Any use, reproduction, disclosure or
# distribution of this software and related documentation without an express
# license agreement from NVIDIA CORPORATION is strictly prohibited.

# Enable or Disable Riva Services
service_enabled_asr=false
service_enabled_nlp=false
service_enabled_tts=false

# Specify one or more GPUs to use
# specifying more than one GPU is currently an experimental feature, and may result in undefined behaviours.
gpus_to_use="device=0"

# Specify the encryption key to use to deploy models
MODEL_DEPLOY_KEY="tlt_encode"

# Locations to use for storing models artifacts
#
# If an absolute path is specified, the data will be written to that location
# Otherwise, a docker volume will be used (default).
#
# riva_init.sh will create a `rmir` and `models` directory in the volume or
# path specified. 
#
# RMIR ($riva_model_loc/rmir)
# Riva uses an intermediate representation (RMIR) for models
# that are ready to deploy but not yet fully optimized for deployment. Pretrained
# versions can be obtained from NGC (by specifying NGC models below) and will be
# downloaded to $riva_model_loc/rmir by `riva_init.sh`
# 
# Custom models produced by NeMo or TLT and prepared using riva-build
# may also be copied manually to this location $(riva_model_loc/rmir).
#
# Models ($riva_model_loc/models)
# During the riva_init process, the RMIR files in $riva_model_loc/rmir
# are inspected and optimized for deployment. The optimized versions are
# stored in $riva_model_loc/models. The riva server exclusively uses these
# optimized versions.
riva_model_loc="riva-model-repo"

# The default RMIRs are downloaded from NGC by default in the above $riva_rmir_loc directory
# If you'd like to skip the download from NGC and use the existing RMIRs in the $riva_rmir_loc
# then set the below $use_existing_rmirs flag to true. You can also deploy your set of custom
# RMIRs by keeping them in the riva_rmir_loc dir and use this quickstart script with the
# below flag to deploy them all together.
use_existing_rmirs=true

# Ports to expose for Riva services
riva_speech_api_port="50051"
riva_vision_api_port="60051"

# NGC orgs
riva_ngc_org="nvidia"
riva_ngc_team="riva"
riva_ngc_image_version="1.6.0-beta"
riva_ngc_model_version="1.6.0-beta"

# Pre-built models listed below will be downloaded from NGC. If models already exist in $riva-rmir
# then models can be commented out to skip download from NGC

########## ASR MODELS ##########

models_asr=(
### Punctuation model
    "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_punctuation_bert_base:${riva_ngc_model_version}"

### Citrinet-1024 Streaming w/ CPU decoder, best latency configuration
    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_citrinet_1024_asrset3p0_streaming:${riva_ngc_model_version}"

### Citrinet-1024 Streaming w/ CPU decoder, best throughput configuration
#    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_citrinet_1024_asrset3p0_streaming_throughput:${riva_ngc_model_version}"

### Citrinet-1024 Offline w/ CPU decoder, 
    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_citrinet_1024_asrset3p0_offline:${riva_ngc_model_version}"

### Jasper Streaming w/ CPU decoder, best latency configuration
#    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_english_streaming:${riva_ngc_model_version}"

### Jasper Streaming w/ CPU decoder, best throughput configuration
#    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_english_streaming_throughput:${riva_ngc_model_version}"

###  Jasper Offline w/ CPU decoder
#    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_english_offline:${riva_ngc_model_version}"
 
### Quarztnet Streaming w/ CPU decoder, best latency configuration
#    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_quartznet_english_streaming:${riva_ngc_model_version}"

### Quarztnet Streaming w/ CPU decoder, best throughput configuration
#    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_quartznet_english_streaming_throughput:${riva_ngc_model_version}"

### Quarztnet Offline w/ CPU decoder
#    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_quartznet_english_offline:${riva_ngc_model_version}"

### Jasper Streaming w/ GPU decoder, best latency configuration
#    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_english_streaming_gpu_decoder:${riva_ngc_model_version}"

### Jasper Streaming w/ GPU decoder, best throughput configuration
#    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_english_streaming_throughput_gpu_decoder:${riva_ngc_model_version}"

### Jasper Offline w/ GPU decoder
#    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_english_offline_gpu_decoder:${riva_ngc_model_version}"
)

########## NLP MODELS ##########

models_nlp=(
### Bert base Punctuation model
    "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_punctuation_bert_base:${riva_ngc_model_version}"

### BERT base Named Entity Recognition model fine-tuned on GMB dataset with class labels LOC, PER, ORG etc.
    "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_named_entity_recognition_bert_base:${riva_ngc_model_version}"

### BERT Base Intent Slot model fine-tuned on weather dataset.
    "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_intent_slot_bert_base:${riva_ngc_model_version}"

### BERT Base Question Answering model fine-tuned on Squad v2.
    "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_question_answering_bert_base:${riva_ngc_model_version}"

### Megatron345M Question Answering model fine-tuned on Squad v2.
#    "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_question_answering_megatron:${riva_ngc_model_version}"

### Bert base Text Classification model fine-tuned on 4class (weather, meteorology, personality, nomatch) domain model.
    "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_text_classification_bert_base:${riva_ngc_model_version}"
)

########## TTS MODELS ##########

models_tts=(
   "${riva_ngc_org}/${riva_ngc_team}/rmir_tts_fastpitch_hifigan_ljspeech:${riva_ngc_model_version}"
#   "${riva_ngc_org}/${riva_ngc_team}/rmir_tts_tacotron_waveglow_ljspeech:${riva_ngc_model_version}"
)

NGC_TARGET=${riva_ngc_org}
if [[ ! -z ${riva_ngc_team} ]]; then
  NGC_TARGET="${NGC_TARGET}/${riva_ngc_team}"
else
  team="\"\""
fi

# define docker images required to run Riva
image_client="nvcr.io/${NGC_TARGET}/riva-speech-client:${riva_ngc_image_version}"
image_speech_api="nvcr.io/${NGC_TARGET}/riva-speech:${riva_ngc_image_version}-server"

# define docker images required to setup Riva
image_init_speech="nvcr.io/${NGC_TARGET}/riva-speech:${riva_ngc_image_version}-servicemaker"

# daemon names
riva_daemon_speech="riva-speech"
riva_daemon_client="riva-client"

riva_init.sh

#!/bin/bash
# Copyright (c) 2021, NVIDIA CORPORATION.  All rights reserved.
#
# NVIDIA CORPORATION and its licensors retain all intellectual property
# and proprietary rights in and to this software, related documentation
# and any modifications thereto.  Any use, reproduction, disclosure or
# distribution of this software and related documentation without an express
# license agreement from NVIDIA CORPORATION is strictly prohibited.


get_ngc_key_from_environment() {
    # first check the global NGC_API_KEY environment variable
    local ngc_key=$NGC_API_KEY
    # if env variable was not set, and a ~/.ngc/config exists
    # try to get it from there
    if [ -z "$ngc_key" ] && [[ -f "$HOME/.ngc/config" ]]
    then
        ngc_key=$(cat $HOME/.ngc/config | grep -m 1 -G "^\s*apikey\s*=.*" | sed 's/^\s*apikey\s*=\s*//g')
    fi
    echo $ngc_key
}

docker_pull() {
    image_exists=$(docker images --filter=reference=$1 -q | wc -l)
    if [[ $image_exists -eq 1 ]]; then
        echo "  > Image $1 exists. Skipping."
        return
    fi
    attempts=3
    echo "  > Pulling $1. This may take some time..."
    for ((i = 1 ; i <= $attempts ; i++)); do
        docker pull -q $1 &> /dev/null
        if [ $? -ne 0 ]; then
            echo "  > Attempt $i out of $attempts failed"
            if [ $i -eq $attempts ]; then
                echo "Error occurred pulling '$1'."
                docker pull $1
                echo "Exiting."
                exit 1
            else
                echo "  > Trying again..."
                continue
            fi
        else
            break
        fi
    done
}

check_docker_version() {
    version_string=$(docker version --format '{{.Server.Version}}')
    if [ $? -ne 0 ]; then
        echo "Unable to run Docker. Please check that Docker is installed and functioning."
        exit 1
    fi
    maj_ver=$(echo $version_string | awk -F. '{print $1}')
    min_ver=$(echo $version_string | awk -F. '{print $2}')
    if [ "$maj_ver" -lt "19" ] || ([ "$maj_ver" -eq "19" ] && [ "$min_ver" -lt "03" ]); then
        echo "Docker version insufficient. Please use Docker 19.03 or later"
        exit 1;
    fi
}

# BEGIN SCRIPT
#check_docker_version

# load config file
script_path="$( cd "$(dirname "$0")" >/dev/null 2>&1 ; pwd -P )"
if [ -z "$1" ]; then
    config_path="${script_path}/config.sh"
else
    config_path=$(readlink -f $1)
fi

if [[ ! -f $config_path ]]; then
    echo 'Unable to load configuration file. Override path to file with -c argument.'
    exit 1
fi
source $config_path || exit 1

# automatically get NGC_API_KEY or request from user if necessary
#NGC_API_KEY="$(get_ngc_key_from_environment)"
#if [ -z "$NGC_API_KEY" ]; then
#    read -sp 'Please enter API key for ngc.nvidia.com: ' NGC_API_KEY
#    echo
#fi

# use the API key to run docker login for the NGC registry
# exit early if the key is invalid, because we won't be able to do anything
#echo "Logging into NGC docker registry if necessary..."
#echo $NGC_API_KEY | docker login -u '$oauthtoken' --password-stdin nvcr.io &> /dev/null
#if [ $? -ne 0 ]; then
#    echo 'NGC API Key is invalid. Please check and try again.'
#    exit 1
#fi

# pull all the requisite images we're going to need
echo "Pulling required docker images if necessary..."
echo "Note: This may take some time, depending on the speed of your Internet connection."
# pull the speech server if any of asr/nlp/tts services are requested
if [ "$service_enabled_asr" = true ] || [ "$service_enabled_nlp" = true ] || [ "$service_enabled_tts" = true ]; then
    echo "> Pulling Riva Speech Server images."
    docker_pull $image_speech_api
    docker_pull $image_client
    docker_pull $image_init_speech
fi


if [ "$use_existing_rmirs" = false ]; then
    echo
    echo "Downloading models (RMIRs) from NGC..."
    echo "Note: this may take some time, depending on the speed of your Internet connection."
    echo "To skip this process and use existing RMIRs set the location and corresponding flag in config.sh."

    # build up commands to download from NGC
    if [ "$service_enabled_asr" = true ] || [ "$service_enabled_nlp" = true ] || [ "$service_enabled_tts" = true ]; then
        gmr_speech_models=""
        if [ "$service_enabled_asr" = true ]; then
            for model in ${models_asr[@]}; do
                gmr_speech_models+=" $model"
            done
        fi
        if [ "$service_enabled_nlp" = true ]; then
            for model in ${models_nlp[@]}; do
                gmr_speech_models+=" $model"
            done
        fi
        if [ "$service_enabled_tts" = true ]; then
            for model in ${models_tts[@]}; do
                gmr_speech_models+=" $model"
            done
        fi

        # download required images
        docker run --init -it --rm --gpus '"'$gpus_to_use'"'  \
          -v $riva_model_loc:/data \
          -e "NGC_CLI_API_KEY=$NGC_API_KEY" \
          -e "NGC_CLI_ORG=nvidia" \
          --name riva-service-maker \
          $image_init_speech download_ngc_models $gmr_speech_models

        if [ $? -ne 0 ]; then
            echo "Error in downloading models."
            exit 1
        fi
    fi
fi

# convert all rmirs
echo
echo "Converting RMIRs at $riva_model_loc/rmir to Riva Model repository."

set -x
docker run --init -it --rm --gpus '"'$gpus_to_use'"' \
  -v $riva_model_loc:/data \
  -e "MODEL_DEPLOY_KEY=${MODEL_DEPLOY_KEY}" \
          --name riva-service-maker \
  $image_init_speech deploy_all_models /data/rmir /data/models

echo
echo "Riva initialization complete. Run ./riva_start.sh to launch services."
#10

Hi,

Please refer following doc for more details.
https://docs.nvidia.com/deeplearning/riva/user-guide/docs/custom-model-deployment.html?highlight=model_loc#option-1-using-quick-start-scripts-to-deploy-your-models-recommended-path

Thank you.

#11

Thanks, @spolisetty
I’m planning to host Riva on another server with internet to ease the setup process, however, the GPU spec is

NVIDIA Tesla T4 16GB x1

I’m wondering whether this kind of GPU is powerful enough to host Riva.

According to the support matrix, only the following GPU is supporting Riva,

  • NVIDIA A100
  • NVIDIA Volta V100
  • NVIDIA Turing T4

Is NVIDIA Turing T4 as same as NVIDIA Tesla T4?

#12

I am having the same issue, as I run:

/riva_quickstart_v2.3.0# bash riva_start.sh

…then:

/riva_quickstart_v2.3.0# docker logs riva-speech

I0818 17:06:19.992784 105 model_repository_manager.cc:1132] successfully unloaded ‘citrinet-1024-en-US-asr-offline-ctc-decoder-cpu-offline’ version 1

Riva waiting for Triton server to load all models…retrying in 1 second

I0818 17:06:20.434286 105 server.cc:267] Timeout 29: Found 0 live models and 0 in-flight non-inference requests

error: creating server: Internal - failed to load all models

W0818 17:06:20.453564 105 metrics.cc:401] Unable to get power limit for GPU 0. Status:Success, value:0.000000

W0818 17:06:20.453699 105 metrics.cc:419] Unable to get power usage for GPU 0. Status:Success, value:0.000000

W0818 17:06:20.453771 105 metrics.cc:443] Unable to get energy consumption for GPU 0. Status:Success, value:0

Riva waiting for Triton server to load all models…retrying in 1 second

W0818 17:06:21.453974 105 metrics.cc:401] Unable to get power limit for GPU 0. Status:Success, value:0.000000

W0818 17:06:21.454103 105 metrics.cc:419] Unable to get power usage for GPU 0. Status:Success, value:0.000000

W0818 17:06:21.454173 105 metrics.cc:443] Unable to get energy consumption for GPU 0. Status:Success, value:0

Riva waiting for Triton server to load all models…retrying in 1 second

Triton server died before reaching ready state. Terminating Riva startup.

Check Triton logs with: docker logs

/opt/riva/bin/start-riva: line 1: kill: (105) - No such process

My config.sh:



# Copyright (c) 2022, NVIDIA CORPORATION.  All rights reserved.
#
# NVIDIA CORPORATION and its licensors retain all intellectual property
# and proprietary rights in and to this software, related documentation
# and any modifications thereto.  Any use, reproduction, disclosure or
# distribution of this software and related documentation without an express
# license agreement from NVIDIA CORPORATION is strictly prohibited.

# Architecture of target platform. Supported architectures: amd64, arm64
riva_target_arch="amd64"

# Legacy arm64 platform to be enabled. Supported legacy platforms: xavier
riva_arm64_legacy_platform=""

# Enable or Disable Riva Services
service_enabled_asr=true
service_enabled_nlp=false
service_enabled_tts=false

# Enable Riva Enterprise
# If enrolled in Enterprise, enable Riva Enterprise by setting configuration
# here. You must explicitly acknowledge you have read and agree to the EULA.
# RIVA_API_KEY=<ngc api key>
# RIVA_API_NGC_ORG=<ngc organization>
# RIVA_EULA=accept

# Language code to fetch models of a specify language
# Currently only ASR supports languages other than English
# Supported language codes: en-US, de-DE, es-US, ru-RU, zh-CN, hi-IN
# for any language other than English, set service_enabled_nlp and service_enabled_tts to False
# for multiple languages enter space separated language codes.
language_code=("en-US")

# Specify one or more GPUs to use
# specifying more than one GPU is currently an experimental feature, and may result in undefined behaviours.
gpus_to_use="device=0"

# Specify the encryption key to use to deploy models
MODEL_DEPLOY_KEY="tlt_encode"

# Locations to use for storing models artifacts
#
# If an absolute path is specified, the data will be written to that location
# Otherwise, a docker volume will be used (default).
#
# riva_init.sh will create a `rmir` and `models` directory in the volume or
# path specified.
#
# RMIR ($riva_model_loc/rmir)
# Riva uses an intermediate representation (RMIR) for models
# that are ready to deploy but not yet fully optimized for deployment. Pretrained
# versions can be obtained from NGC (by specifying NGC models below) and will be
# downloaded to $riva_model_loc/rmir by `riva_init.sh`
#
# Custom models produced by NeMo or TLT and prepared using riva-build
# may also be copied manually to this location $(riva_model_loc/rmir).
#
# Models ($riva_model_loc/models)
# During the riva_init process, the RMIR files in $riva_model_loc/rmir
# are inspected and optimized for deployment. The optimized versions are
# stored in $riva_model_loc/models. The riva server exclusively uses these
# optimized versions.
riva_model_loc="riva-model-repo"

if [[ $riva_target_arch == "arm64" ]]; then
    riva_model_loc="`pwd`/model_repository"
fi

# The default RMIRs are downloaded from NGC by default in the above $riva_rmir_loc directory
# If you'd like to skip the download from NGC and use the existing RMIRs in the $riva_rmir_loc
# then set the below $use_existing_rmirs flag to true. You can also deploy your set of custom
# RMIRs by keeping them in the riva_rmir_loc dir and use this quickstart script with the
# below flag to deploy them all together.
use_existing_rmirs=false

# Ports to expose for Riva services
riva_speech_api_port="50051"

# NGC orgs
riva_ngc_org="nvidia"
riva_ngc_team="riva"
riva_ngc_image_version="2.3.0"
riva_ngc_model_version="2.3.0"

# Pre-built models listed below will be downloaded from NGC. If models already exist in $riva-rmir
# then models can be commented out to skip download from NGC

########## ASR MODELS ##########

models_asr=()

### Citrinet-1024 models
for lang_code in ${language_code[@]}; do
    modified_lang_code="${lang_code/-/_}"
    modified_lang_code=${modified_lang_code,,}
    if [[ $riva_target_arch == "arm64" ]]; then
      models_asr+=(
      ### Citrinet-1024 Streaming w/ CPU decoder, best latency configuration
          "${riva_ngc_org}/${riva_ngc_team}/models_asr_citrinet_1024_${modified_lang_code}_str:${riva_ngc_model_version}-${riva_target_arch}${riva_arm64_legacy_platform}"
      )
    else
      models_asr+=(
      ### Citrinet-1024 Streaming w/ CPU decoder, best latency configuration
          "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_citrinet_1024_${modified_lang_code}_str:${riva_ngc_model_version}"

      ### Citrinet-1024 Streaming w/ CPU decoder, best throughput configuration
      #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_citrinet_1024_${modified_lang_code}_str_thr:${riva_ngc_model_version}"

      ### Citrinet-1024 Offline w/ CPU decoder,
          "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_citrinet_1024_${modified_lang_code}_ofl:${riva_ngc_model_version}"
      )
    fi

    ### Punctuation model
    if [[ "${lang_code}"  == "en-US" || "${lang_code}" == "de-DE" || "${lang_code}" == "es-US" || "${lang_code}" == "zh-CN" ]]; then
      if [[ $riva_target_arch == "arm64" ]]; then
        models_asr+=(
            "${riva_ngc_org}/${riva_ngc_team}/models_nlp_punctuation_bert_base_${modified_lang_code}:${riva_ngc_model_version}-${riva_target_arch}${riva_arm64_legacy_platform}"
        )
      else
        models_asr+=(
            "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_punctuation_bert_base_${modified_lang_code}:${riva_ngc_model_version}"
        )
      fi
    fi

done

#Other ASR models
if [[ $riva_target_arch == "arm64" ]]; then
  models_asr+=(
  ### Conformer acoustic model, CPU decoder, streaming best latency configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/models_asr_conformer_en_us_str:${riva_ngc_model_version}-${riva_target_arch}${riva_arm64_legacy_platform}"

  ### German Conformer acoustic model, CPU decoder, streaming best latency configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/models_asr_conformer_de_de_str:${riva_ngc_model_version}-${riva_target_arch}${riva_arm64_legacy_platform}"

  ### Spanish Conformer acoustic model, CPU decoder, streaming best latency configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/models_asr_conformer_es_us_str:${riva_ngc_model_version}-${riva_target_arch}${riva_arm64_legacy_platform}"

  ### Hindi Conformer acoustic model, CPU decoder, streaming best latency configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/models_asr_conformer_hi_in_str:${riva_ngc_model_version}-${riva_target_arch}${riva_arm64_legacy_platform}"

  ### Russian Conformer acoustic model, CPU decoder, streaming best latency configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/models_asr_conformer_ru_ru_str:${riva_ngc_model_version}-${riva_target_arch}${riva_arm64_legacy_platform}"

  ### Citrinet-256 Streaming w/ CPU decoder, best latency configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/models_asr_citrinet_256_en_us_streaming:${riva_ngc_model_version}-${riva_target_arch}${riva_arm64_legacy_platform}"
  )
else
  models_asr+=(
  ### Conformer acoustic model, CPU decoder, streaming best latency configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_en_us_str:${riva_ngc_model_version}"

  ### Conformer acoustic model, CPU decoder, streaming best throughput configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_en_us_str_thr:${riva_ngc_model_version}"

  ### Conformer acoustic model, CPU decoder, offline configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_en_us_ofl:${riva_ngc_model_version}"

  ### German Conformer acoustic model, CPU decoder, streaming best latency configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_de_de_str:${riva_ngc_model_version}"

  ### German Conformer acoustic model, CPU decoder, streaming best throughput configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_de_de_str_thr:${riva_ngc_model_version}"

  ### German Conformer acoustic model, CPU decoder, offline configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_de_de_ofl:${riva_ngc_model_version}"

  ### Spanish Conformer acoustic model, CPU decoder, streaming best latency configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_es_us_str:${riva_ngc_model_version}"

  ### Spanish Conformer acoustic model, CPU decoder, streaming best throughput configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_es_us_str_thr:${riva_ngc_model_version}"

  ### Spanish Conformer acoustic model, CPU decoder, offline configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_es_us_ofl:${riva_ngc_model_version}"

  ### Hindi Conformer acoustic model, CPU decoder, streaming best latency configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_hi_in_str:${riva_ngc_model_version}"

  ### Hindi Conformer acoustic model, CPU decoder, streaming best throughput configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_hi_in_str_thr:${riva_ngc_model_version}"

  ### Hindi Conformer acoustic model, CPU decoder, offline configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_hi_in_ofl:${riva_ngc_model_version}"
  
  ### Russian Conformer acoustic model, CPU decoder, streaming best latency configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_ru_ru_str:${riva_ngc_model_version}"

  ### Russian Conformer acoustic model, CPU decoder, streaming best throughput configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_ru_ru_str_thr:${riva_ngc_model_version}"

  ### Russian Conformer acoustic model, CPU decoder, offline configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_conformer_ru_ru_ofl:${riva_ngc_model_version}"

  ### Jasper Streaming w/ CPU decoder, best latency configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_en_us_str:${riva_ngc_model_version}"

  ### Jasper Streaming w/ CPU decoder, best throughput configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_en_us_str_thr:${riva_ngc_model_version}"

  ###  Jasper Offline w/ CPU decoder
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_en_us_ofl:${riva_ngc_model_version}"

  ### Quarztnet Streaming w/ CPU decoder, best latency configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_quartznet_en_us_str:${riva_ngc_model_version}"

  ### Quarztnet Streaming w/ CPU decoder, best throughput configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_quartznet_en_us_str_thr:${riva_ngc_model_version}"

  ### Quarztnet Offline w/ CPU decoder
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_quartznet_en_us_ofl:${riva_ngc_model_version}"

  ### Jasper Streaming w/ GPU decoder, best latency configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_en_us_str_gpu_decoder:${riva_ngc_model_version}"

  ### Jasper Streaming w/ GPU decoder, best throughput configuration
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_en_us_str_thr_gpu_decoder:${riva_ngc_model_version}"

  ### Jasper Offline w/ GPU decoder
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_asr_jasper_en_us_ofl_gpu_decoder:${riva_ngc_model_version}"
  )
fi

########## NLP MODELS ##########

if [[ $riva_target_arch == "arm64" ]]; then
  models_nlp=(
  ### BERT Base Intent Slot model for misty domain fine-tuned on weather, smalltalk/personality, poi/map datasets.
      "${riva_ngc_org}/${riva_ngc_team}/models_nlp_intent_slot_misty_bert_base:${riva_ngc_model_version}-${riva_target_arch}${riva_arm64_legacy_platform}"

  ### DistilBERT Intent Slot model for misty domain fine-tuned on weather, smalltalk/personality, poi/map datasets.
  #    "${riva_ngc_org}/${riva_ngc_team}/models_nlp_intent_slot_misty_distilbert:${riva_ngc_model_version}-${riva_target_arch}${riva_arm64_legacy_platform}"
  )
else
  models_nlp=(
  ### Bert base Punctuation model
      "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_punctuation_bert_base_en_us:${riva_ngc_model_version}"

  ### BERT base Named Entity Recognition model fine-tuned on GMB dataset with class labels LOC, PER, ORG etc.
      "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_named_entity_recognition_bert_base:${riva_ngc_model_version}"

  ### BERT Base Intent Slot model fine-tuned on weather dataset.
      "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_intent_slot_bert_base:${riva_ngc_model_version}"

  ### BERT Base Question Answering model fine-tuned on Squad v2.
      "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_question_answering_bert_base:${riva_ngc_model_version}"

  ### Megatron345M Question Answering model fine-tuned on Squad v2.
  #    "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_question_answering_megatron:${riva_ngc_model_version}"

  ### Bert base Text Classification model fine-tuned on 4class (weather, meteorology, personality, nomatch) domain model.
      "${riva_ngc_org}/${riva_ngc_team}/rmir_nlp_text_classification_bert_base:${riva_ngc_model_version}"
  )
fi

########## TTS MODELS ##########

if [[ $riva_target_arch == "arm64" ]]; then
  models_tts=(
     "${riva_ngc_org}/${riva_ngc_team}/models_tts_fastpitch_hifigan_en_us_female_1:${riva_ngc_model_version}-${riva_target_arch}${riva_arm64_legacy_platform}"
  #   "${riva_ngc_org}/${riva_ngc_team}/models_tts_fastpitch_hifigan_en_us_male_1:${riva_ngc_model_version}-${riva_target_arch}${riva_arm64_legacy_platform}"
  )
else
  models_tts=(
     "${riva_ngc_org}/${riva_ngc_team}/rmir_tts_fastpitch_hifigan_en_us_female_1:${riva_ngc_model_version}"
  #   "${riva_ngc_org}/${riva_ngc_team}/rmir_tts_fastpitch_hifigan_en_us_male_1:${riva_ngc_model_version}"
  )
fi

NGC_TARGET=${riva_ngc_org}
if [[ ! -z ${riva_ngc_team} ]]; then
  NGC_TARGET="${NGC_TARGET}/${riva_ngc_team}"
else
  team="\"\""
fi

# Specify paths to SSL Key and Certificate files to use TLS/SSL Credentials for a secured connection.
# If either are empty, an insecure connection will be used.
# Stored within container at /ssl/servert.crt and /ssl/server.key
# Optional, one can also specify a root certificate, stored within container at /ssl/root_server.crt
ssl_server_cert=""
ssl_server_key=""
ssl_root_cert=""

# define docker images required to run Riva
image_client="nvcr.io/${NGC_TARGET}/riva-speech-client:${riva_ngc_image_version}"
image_speech_api="nvcr.io/${NGC_TARGET}/riva-speech:${riva_ngc_image_version}-server"

# define docker images required to setup Riva
image_init_speech="nvcr.io/${NGC_TARGET}/riva-speech:${riva_ngc_image_version}-servicemaker"

# daemon names
riva_daemon_speech="riva-speech"
if [[ $riva_target_arch != "arm64" ]]; then
    riva_daemon_client="riva-client"
fi

As other posts suggested, I ran clean-up:

bash riva_clean.sh

results via docker logs riva-speech:

error: creating server: Invalid argument - --model-repository must be specified

…as follows:

Screen Shot 2022-08-18 at 12.11.40 PM
Screen Shot 2022-08-18 at 12.11.40 PM2860×1582 338 KB

Environment Details:
Ubuntu 22.04.1 LTS
NVIDIA Driver Version: 510.73.08 (GPU A100)
CUDA Version: 11.6
Docker: 20.10.17

Any thoughts?

Thank you.

#13

Hi @NSDB

Thanks for your interest in Riva,

To triage the issue, we may need the following information

Please clean the setup using bash riva_clean.sh

  1. Complete log out of bash riva_init.sh and attach as file in this thread
  2. Run the command docker volume inspect riva-model-repo and share with us the output in this thread
  3. From the above command output, under the key “Mountpoint” there would be a path, we request to ls <Add-Path-present-in-Mountpoint>/models and share the output
  4. Complete log output of command docker logs riva-speech and attach as file in this thread

Thanks

#14

Per your request:

docker volume inspect riva-model-repo:

root@tengine:~/riva_quickstart_v2.4.0# docker volume inspect riva-model-repo
[
	{
		"CreatedAt": "2022-08-23T17:44:14Z",
		"Driver": "local",
		"Labels": null,
		"Mountpoint": "/var/lib/docker/volumes/riva-model-repo/_data",
		"Name": "riva-model-repo",
		"Options": null,
		"Scope": "local"
	}
]

ls /models:


riva_quickstart_v2.4.0# ls /var/lib/docker/volumes/riva-model-repo/_data/models/
conformer-en-US-asr-offline                                                conformer-en-US-asr-streaming-feature-extractor-streaming
conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline              conformer-en-US-asr-streaming-voice-activity-detector-ctc-streaming
conformer-en-US-asr-offline-feature-extractor-streaming-offline            riva-punctuation-en-US
conformer-en-US-asr-offline-voice-activity-detector-ctc-streaming-offline  riva-trt-conformer-en-US-asr-offline-am-streaming-offline
conformer-en-US-asr-streaming                                              riva-trt-conformer-en-US-asr-streaming-am-streaming
conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming                    riva-trt-riva-punctuation-en-US-nn-bert-base-uncased

docker logs riva-speech

root@tengine:~/riva_quickstart_v2.4.0# docker logs riva-speech

Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Health ready check failed.
Check Riva logs with: docker logs riva-speech
root@tengine:~/riva_quickstart_v2.4.0#  docker logs riva-speech

==========================
=== Riva Speech Skills ===
==========================

NVIDIA Release 22.07 (build 42007163)
Riva Speech Server Version 2.4.0

Copyright (c) 2018-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.

Various files include modifications (c) NVIDIA CORPORATION & AFFILIATES.  All rights reserved.

This container image and its contents are governed by the NVIDIA Deep Learning Container License.
By pulling and using the container, you accept the terms and conditions of this license:
https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license

  > Riva waiting for Triton server to load all models...retrying in 1 second
I0824 23:02:02.207992 101 onnxruntime.cc:2400] TRITONBACKEND_Initialize: onnxruntime
I0824 23:02:02.208177 101 onnxruntime.cc:2410] Triton TRITONBACKEND API version: 1.9
I0824 23:02:02.208487 101 onnxruntime.cc:2416] 'onnxruntime' TRITONBACKEND API version: 1.9
I0824 23:02:02.208554 101 onnxruntime.cc:2446] backend configuration:
{}
I0824 23:02:02.712583 101 pinned_memory_manager.cc:240] Pinned memory pool is created at '0x10020000000' with size 268435456
I0824 23:02:02.712969 101 cuda_memory_manager.cc:105] CUDA memory pool is created on device 0 with size 1000000000
E0824 23:02:02.719851 101 model_repository_manager.cc:2064] Poll failed for model directory 'riva-trt-conformer-en-US-asr-streaming-am-streaming': failed to open text file for read /data/models/riva-trt-conformer-en-US-asr-streaming-am-streaming/config.pbtxt: No such file or directory
E0824 23:02:02.720555 101 model_repository_manager.cc:1420] Invalid argument: ensemble conformer-en-US-asr-streaming contains models that are not available: riva-trt-conformer-en-US-asr-streaming-am-streaming
I0824 23:02:02.720745 101 model_repository_manager.cc:1077] loading: conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline:1
I0824 23:02:02.821009 101 model_repository_manager.cc:1077] loading: conformer-en-US-asr-offline-feature-extractor-streaming-offline:1
I0824 23:02:02.864406 101 ctc-decoder-library.cc:20] TRITONBACKEND_ModelInitialize: conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline (version 1)
WARNING: Logging before InitGoogleLogging() is written to STDERR
W0824 23:02:02.865731   107 parameter_parser.cc:120] Parameter forerunner_start_offset_ms could not be set from parameters
W0824 23:02:02.865850   107 parameter_parser.cc:121] Default value will be used
W0824 23:02:02.865895   107 parameter_parser.cc:120] Parameter use_vad could not be set from parameters
W0824 23:02:02.865929   107 parameter_parser.cc:121] Default value will be used
W0824 23:02:02.866024   107 parameter_parser.cc:120] Parameter forerunner_start_offset_ms could not be set from parameters
W0824 23:02:02.866072   107 parameter_parser.cc:121] Default value will be used
W0824 23:02:02.866107   107 parameter_parser.cc:120] Parameter max_num_slots could not be set from parameters
W0824 23:02:02.866155   107 parameter_parser.cc:121] Default value will be used
W0824 23:02:02.866194   107 parameter_parser.cc:120] Parameter use_vad could not be set from parameters
W0824 23:02:02.866237   107 parameter_parser.cc:121] Default value will be used
I0824 23:02:02.866689 101 backend_model.cc:255] model configuration:
{
    "name": "conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline",
    "platform": "",
    "backend": "riva_asr_decoder",
    "version_policy": {
        "latest": {
            "num_versions": 1
        }
    },
    "max_batch_size": 1024,
    "input": [
        {
            "name": "CLASS_LOGITS",
            "data_type": "TYPE_FP32",
            "format": "FORMAT_NONE",
            "dims": [
                -1,
                257
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        },
        {
            "name": "END_FLAG",
            "data_type": "TYPE_UINT32",
            "format": "FORMAT_NONE",
            "dims": [
                1
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        },
        {
            "name": "SEGMENTS_START_END",
            "data_type": "TYPE_FP32",
            "format": "FORMAT_NONE",
            "dims": [
                -1,
                2
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        },
        {
            "name": "CUSTOM_CONFIGURATION",
            "data_type": "TYPE_STRING",
            "format": "FORMAT_NONE",
            "dims": [
                -1,
                2
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        }
    ],
    "output": [
        {
            "name": "FINAL_TRANSCRIPTS",
            "data_type": "TYPE_STRING",
            "dims": [
                -1
            ],
            "label_filename": "",
            "is_shape_tensor": false
        },
        {
            "name": "FINAL_TRANSCRIPTS_SCORE",
            "data_type": "TYPE_FP32",
            "dims": [
                -1
            ],
            "label_filename": "",
            "is_shape_tensor": false
        },
        {
            "name": "FINAL_WORDS_START_END",
            "data_type": "TYPE_INT32",
            "dims": [
                -1,
                2
            ],
            "label_filename": "",
            "is_shape_tensor": false
        },
        {
            "name": "PARTIAL_TRANSCRIPTS",
            "data_type": "TYPE_STRING",
            "dims": [
                -1
            ],
            "label_filename": "",
            "is_shape_tensor": false
        },
        {
            "name": "PARTIAL_TRANSCRIPTS_STABILITY",
            "data_type": "TYPE_FP32",
            "dims": [
                -1
            ],
            "label_filename": "",
            "is_shape_tensor": false
        },
        {
            "name": "PARTIAL_WORDS_START_END",
            "data_type": "TYPE_INT32",
            "dims": [
                -1,
                2
            ],
            "label_filename": "",
            "is_shape_tensor": false
        }
    ],
    "batch_input": [],
    "batch_output": [],
    "optimization": {
        "graph": {
            "level": 0
        },
        "priority": "PRIORITY_DEFAULT",
        "cuda": {
            "graphs": false,
            "busy_wait_events": false,
            "graph_spec": [],
            "output_copy_stream": true
        },
        "input_pinned_memory": {
            "enable": true
        },
        "output_pinned_memory": {
            "enable": true
        },
        "gather_kernel_buffer_threshold": 0,
        "eager_batching": false
    },
    "sequence_batching": {
        "oldest": {
            "max_candidate_sequences": 1024,
            "preferred_batch_size": [
                32,
                64
            ],
            "max_queue_delay_microseconds": 1000
        },
        "max_sequence_idle_microseconds": 60000000,
        "control_input": [
            {
                "name": "START",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_START",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            },
            {
                "name": "READY",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_READY",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            },
            {
                "name": "END",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_END",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            },
            {
                "name": "CORRID",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_CORRID",
                        "int32_false_true": [],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_UINT64"
                    }
                ]
            }
        ],
        "state": []
    },
    "instance_group": [
        {
            "name": "conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline_0",
            "kind": "KIND_CPU",
            "count": 1,
            "gpus": [],
            "secondary_devices": [],
            "profile": [],
            "passive": false,
            "host_policy": ""
        }
    ],
    "default_model_filename": "",
    "cc_model_filenames": {},
    "metric_tags": {},
    "parameters": {
        "ms_per_timestep": {
            "string_value": "40"
        },
        "streaming": {
            "string_value": "True"
        },
        "use_subword": {
            "string_value": "True"
        },
        "beam_size": {
            "string_value": "32"
        },
        "right_padding_size": {
            "string_value": "1.6"
        },
        "beam_size_token": {
            "string_value": "16"
        },
        "sil_token": {
            "string_value": "▁"
        },
        "num_tokenization": {
            "string_value": "1"
        },
        "beam_threshold": {
            "string_value": "20.0"
        },
        "language_model_file": {
            "string_value": "/data/models/conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline/1/en_4.0.bin"
        },
        "tokenizer_model": {
            "string_value": "/data/models/conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline/1/8b8f095152034e98b24ab33726708bd0_tokenizer.model"
        },
        "max_execution_batch_size": {
            "string_value": "1024"
        },
        "forerunner_use_lm": {
            "string_value": "true"
        },
        "forerunner_beam_size_token": {
            "string_value": "8"
        },
        "forerunner_beam_threshold": {
            "string_value": "10.0"
        },
        "asr_model_delay": {
            "string_value": "-1"
        },
        "decoder_num_worker_threads": {
            "string_value": "-1"
        },
        "word_insertion_score": {
            "string_value": "1.0"
        },
        "unk_token": {
            "string_value": "<unk>"
        },
        "left_padding_size": {
            "string_value": "1.6"
        },
        "set_default_index_to_unk_token": {
            "string_value": "False"
        },
        "decoder_type": {
            "string_value": "flashlight"
        },
        "forerunner_beam_size": {
            "string_value": "8"
        },
        "unk_score": {
            "string_value": "-inf"
        },
        "max_supported_transcripts": {
            "string_value": "1"
        },
        "chunk_size": {
            "string_value": "4.8"
        },
        "lexicon_file": {
            "string_value": "/data/models/conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline/1/lexicon.txt"
        },
        "smearing_mode": {
            "string_value": "max"
        },
        "log_add": {
            "string_value": "True"
        },
        "blank_token": {
            "string_value": "#"
        },
        "lm_weight": {
            "string_value": "0.8"
        },
        "vocab_file": {
            "string_value": "/data/models/conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline/1/riva_decoder_vocabulary.txt"
        }
    },
    "model_warmup": [],
    "model_transaction_policy": {
        "decoupled": false
    }
}
I0824 23:02:02.867876 101 ctc-decoder-library.cc:23] TRITONBACKEND_ModelInstanceInitialize: conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline_0 (device 0)
I0824 23:02:02.921271 101 model_repository_manager.cc:1077] loading: conformer-en-US-asr-offline-voice-activity-detector-ctc-streaming-offline:1
I0824 23:02:03.021628 101 model_repository_manager.cc:1077] loading: conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming:1
I0824 23:02:03.121994 101 model_repository_manager.cc:1077] loading: conformer-en-US-asr-streaming-feature-extractor-streaming:1
  > Riva waiting for Triton server to load all models...retrying in 1 second
I0824 23:02:03.222297 101 model_repository_manager.cc:1077] loading: conformer-en-US-asr-streaming-voice-activity-detector-ctc-streaming:1
I0824 23:02:03.322647 101 model_repository_manager.cc:1077] loading: riva-punctuation-en-US:1
I0824 23:02:03.501586 101 model_repository_manager.cc:1077] loading: riva-trt-conformer-en-US-asr-offline-am-streaming-offline:1
I0824 23:02:03.602010 101 model_repository_manager.cc:1077] loading: riva-trt-riva-punctuation-en-US-nn-bert-base-uncased:1
  > Riva waiting for Triton server to load all models...retrying in 1 second
I0824 23:02:04.540582   107 ctc-decoder.cc:171] Beam Decoder initialized successfully!
I0824 23:02:04.541307 101 model_repository_manager.cc:1231] successfully loaded 'conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline' version 1
I0824 23:02:04.541934 101 feature-extractor.cc:399] TRITONBACKEND_ModelInitialize: conformer-en-US-asr-offline-feature-extractor-streaming-offline (version 1)
WARNING: Logging before InitGoogleLogging() is written to STDERR
W0824 23:02:04.542941   108 parameter_parser.cc:120] Parameter is_dither_seed_random could not be set from parameters
W0824 23:02:04.543058   108 parameter_parser.cc:121] Default value will be used
W0824 23:02:04.543107   108 parameter_parser.cc:120] Parameter max_batch_size could not be set from parameters
W0824 23:02:04.543138   108 parameter_parser.cc:121] Default value will be used
W0824 23:02:04.543191   108 parameter_parser.cc:120] Parameter max_sequence_idle_microseconds could not be set from parameters
W0824 23:02:04.543226   108 parameter_parser.cc:121] Default value will be used
W0824 23:02:04.543282   108 parameter_parser.cc:120] Parameter preemph_coeff could not be set from parameters
W0824 23:02:04.543315   108 parameter_parser.cc:121] Default value will be used
I0824 23:02:04.609855 101 backend_model.cc:255] model configuration:
{
    "name": "conformer-en-US-asr-offline-feature-extractor-streaming-offline",
    "platform": "",
    "backend": "riva_asr_features",
    "version_policy": {
        "latest": {
            "num_versions": 1
        }
    },
    "max_batch_size": 512,
    "input": [
        {
            "name": "AUDIO_SIGNAL",
            "data_type": "TYPE_FP32",
            "format": "FORMAT_NONE",
            "dims": [
                -1
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        },
        {
            "name": "SAMPLE_RATE",
            "data_type": "TYPE_UINT32",
            "format": "FORMAT_NONE",
            "dims": [
                1
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        }
    ],
    "output": [
        {
            "name": "AUDIO_FEATURES",
            "data_type": "TYPE_FP32",
            "dims": [
                80,
                -1
            ],
            "label_filename": "",
            "is_shape_tensor": false
        },
        {
            "name": "AUDIO_PROCESSED",
            "data_type": "TYPE_FP32",
            "dims": [
                1
            ],
            "label_filename": "",
            "is_shape_tensor": false
        },
        {
            "name": "AUDIO_FEATURES_LENGTH",
            "data_type": "TYPE_INT32",
            "dims": [
                1
            ],
            "label_filename": "",
            "is_shape_tensor": false
        }
    ],
    "batch_input": [],
    "batch_output": [],
    "optimization": {
        "graph": {
            "level": 0
        },
        "priority": "PRIORITY_DEFAULT",
        "cuda": {
            "graphs": false,
            "busy_wait_events": false,
            "graph_spec": [],
            "output_copy_stream": true
        },
        "input_pinned_memory": {
            "enable": true
        },
        "output_pinned_memory": {
            "enable": true
        },
        "gather_kernel_buffer_threshold": 0,
        "eager_batching": false
    },
    "sequence_batching": {
        "oldest": {
            "max_candidate_sequences": 512,
            "preferred_batch_size": [
                256,
                512
            ],
            "max_queue_delay_microseconds": 1000
        },
        "max_sequence_idle_microseconds": 60000000,
        "control_input": [
            {
                "name": "START",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_START",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            },
            {
                "name": "READY",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_READY",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            },
            {
                "name": "END",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_END",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            },
            {
                "name": "CORRID",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_CORRID",
                        "int32_false_true": [],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_UINT64"
                    }
                ]
            }
        ],
        "state": []
    },
    "instance_group": [
        {
            "name": "conformer-en-US-asr-offline-feature-extractor-streaming-offline_0",
            "kind": "KIND_GPU",
            "count": 1,
            "gpus": [
                0
            ],
            "secondary_devices": [],
            "profile": [],
            "passive": false,
            "host_policy": ""
        }
    ],
    "default_model_filename": "",
    "cc_model_filenames": {},
    "metric_tags": {},
    "parameters": {
        "gain": {
            "string_value": "1.0"
        },
        "precalc_norm_time_steps": {
            "string_value": "0"
        },
        "use_utterance_norm_params": {
            "string_value": "False"
        },
        "dither": {
            "string_value": "1e-05"
        },
        "precalc_norm_params": {
            "string_value": "False"
        },
        "norm_per_feature": {
            "string_value": "True"
        },
        "mean": {
            "string_value": "-11.4412,  -9.9334,  -9.1292,  -9.0365,  -9.2804,  -9.5643,  -9.7342, -9.6925,  -9.6333,  -9.2808,  -9.1887,  -9.1422,  -9.1397,  -9.2028, -9.2749,  -9.4776,  -9.9185, -10.1557, -10.3800, -10.5067, -10.3190, -10.4728, -10.5529, -10.6402, -10.6440, -10.5113, -10.7395, -10.7870, -10.6074, -10.5033, -10.8278, -10.6384, -10.8481, -10.6875, -10.5454, -10.4747, -10.5165, -10.4930, -10.3413, -10.3472, -10.3735, -10.6830, -10.8813, -10.6338, -10.3856, -10.7727, -10.8957, -10.8068, -10.7373, -10.6108, -10.3405, -10.2889, -10.3922, -10.4946, -10.3367, -10.4164, -10.9949, -10.7196, -10.3971, -10.1734,  -9.9257,  -9.6557,  -9.1761, -9.6653,  -9.7876,  -9.7230,  -9.7792,  -9.7056,  -9.2702,  -9.4650, -9.2755,  -9.1369,  -9.1174,  -8.9197,  -8.5394,  -8.2614,  -8.1353, -8.1422,  -8.3430,  -8.6655"
        },
        "stddev": {
            "string_value": "2.2668, 3.1642, 3.7079, 3.7642, 3.5349, 3.5901, 3.7640, 3.8424, 4.0145, 4.1475, 4.0457, 3.9048, 3.7709, 3.6117, 3.3188, 3.1489, 3.0615, 3.0362, 2.9929, 3.0500, 3.0341, 3.0484, 3.0103, 2.9474, 2.9128, 2.8669, 2.8332, 2.9411, 3.0378, 3.0712, 3.0190, 2.9992, 3.0124, 3.0024, 3.0275, 3.0870, 3.0656, 3.0142, 3.0493, 3.1373, 3.1135, 3.0675, 2.8828, 2.7018, 2.6296, 2.8826, 2.9325, 2.9288, 2.9271, 2.9890, 3.0137, 2.9855, 3.0839, 2.9319, 2.3512, 2.3795, 2.6191, 2.7555, 2.9326, 2.9931, 3.1543, 3.0855, 2.6820, 3.0566, 3.1272, 3.1663, 3.1836, 3.0018, 2.9089, 3.1727, 3.1626, 3.1086, 2.9804, 3.1107, 3.2998, 3.3697, 3.3716, 3.2487, 3.1597, 3.1181"
        },
        "chunk_size": {
            "string_value": "4.8"
        },
        "max_execution_batch_size": {
            "string_value": "512"
        },
        "sample_rate": {
            "string_value": "16000"
        },
        "window_size": {
            "string_value": "0.025"
        },
        "num_features": {
            "string_value": "80"
        },
        "window_stride": {
            "string_value": "0.01"
        },
        "streaming": {
            "string_value": "True"
        },
        "left_padding_size": {
            "string_value": "1.6"
        },
        "stddev_floor": {
            "string_value": "1e-05"
        },
        "transpose": {
            "string_value": "False"
        },
        "right_padding_size": {
            "string_value": "1.6"
        }
    },
    "model_warmup": [],
    "model_transaction_policy": {
        "decoupled": false
    }
}
I0824 23:02:04.611508 101 vad_library.cc:18] TRITONBACKEND_ModelInitialize: conformer-en-US-asr-offline-voice-activity-detector-ctc-streaming-offline (version 1)
WARNING: Logging before InitGoogleLogging() is written to STDERR
W0824 23:02:04.612211   109 parameter_parser.cc:120] Parameter max_execution_batch_size could not be set from parameters
W0824 23:02:04.612298   109 parameter_parser.cc:121] Default value will be used
W0824 23:02:04.612373   109 parameter_parser.cc:120] Parameter max_execution_batch_size could not be set from parameters
W0824 23:02:04.612419   109 parameter_parser.cc:121] Default value will be used
I0824 23:02:04.612833 101 backend_model.cc:255] model configuration:
{
    "name": "conformer-en-US-asr-offline-voice-activity-detector-ctc-streaming-offline",
    "platform": "",
    "backend": "riva_asr_vad",
    "version_policy": {
        "latest": {
            "num_versions": 1
        }
    },
    "max_batch_size": 2048,
    "input": [
        {
            "name": "CLASS_LOGITS",
            "data_type": "TYPE_FP32",
            "format": "FORMAT_NONE",
            "dims": [
                -1,
                257
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        }
    ],
    "output": [
        {
            "name": "SEGMENTS_START_END",
            "data_type": "TYPE_FP32",
            "dims": [
                -1,
                2
            ],
            "label_filename": "",
            "is_shape_tensor": false
        }
    ],
    "batch_input": [],
    "batch_output": [],
    "optimization": {
        "graph": {
            "level": 0
        },
        "priority": "PRIORITY_DEFAULT",
        "cuda": {
            "graphs": false,
            "busy_wait_events": false,
            "graph_spec": [],
            "output_copy_stream": true
        },
        "input_pinned_memory": {
            "enable": true
        },
        "output_pinned_memory": {
            "enable": true
        },
        "gather_kernel_buffer_threshold": 0,
        "eager_batching": false
    },
    "sequence_batching": {
        "max_sequence_idle_microseconds": 60000000,
        "control_input": [
            {
                "name": "START",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_START",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            },
            {
                "name": "READY",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_READY",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            }
        ],
        "state": []
    },
    "instance_group": [
        {
            "name": "conformer-en-US-asr-offline-voice-activity-detector-ctc-streaming-offline_0",
            "kind": "KIND_CPU",
            "count": 1,
            "gpus": [],
            "secondary_devices": [],
            "profile": [],
            "passive": false,
            "host_policy": ""
        }
    ],
    "default_model_filename": "",
    "cc_model_filenames": {},
    "metric_tags": {},
    "parameters": {
        "vocab_file": {
            "string_value": "/data/models/conformer-en-US-asr-offline-voice-activity-detector-ctc-streaming-offline/1/riva_decoder_vocabulary.txt"
        },
        "residue_blanks_at_start": {
            "string_value": "0"
        },
        "ms_per_timestep": {
            "string_value": "40"
        },
        "use_subword": {
            "string_value": "True"
        },
        "streaming": {
            "string_value": "True"
        },
        "residue_blanks_at_end": {
            "string_value": "0"
        },
        "vad_stop_history": {
            "string_value": "800"
        },
        "vad_start_history": {
            "string_value": "200"
        },
        "chunk_size": {
            "string_value": "4.8"
        },
        "vad_stop_th": {
            "string_value": "0.98"
        },
        "vad_start_th": {
            "string_value": "0.2"
        },
        "vad_type": {
            "string_value": "ctc-vad"
        }
    },
    "model_warmup": [],
    "model_transaction_policy": {
        "decoupled": false
    }
}
I0824 23:02:04.613409 101 ctc-decoder-library.cc:20] TRITONBACKEND_ModelInitialize: conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming (version 1)
W0824 23:02:04.614167   110 parameter_parser.cc:120] Parameter forerunner_start_offset_ms could not be set from parameters
W0824 23:02:04.614225   110 parameter_parser.cc:121] Default value will be used
W0824 23:02:04.614292   110 parameter_parser.cc:120] Parameter use_vad could not be set from parameters
W0824 23:02:04.614327   110 parameter_parser.cc:121] Default value will be used
W0824 23:02:04.614471   110 parameter_parser.cc:120] Parameter forerunner_start_offset_ms could not be set from parameters
W0824 23:02:04.614517   110 parameter_parser.cc:121] Default value will be used
W0824 23:02:04.614552   110 parameter_parser.cc:120] Parameter max_num_slots could not be set from parameters
W0824 23:02:04.614603   110 parameter_parser.cc:121] Default value will be used
W0824 23:02:04.614641   110 parameter_parser.cc:120] Parameter use_vad could not be set from parameters
W0824 23:02:04.614693   110 parameter_parser.cc:121] Default value will be used
I0824 23:02:04.615106 101 backend_model.cc:255] model configuration:
{
    "name": "conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming",
    "platform": "",
    "backend": "riva_asr_decoder",
    "version_policy": {
        "latest": {
            "num_versions": 1
        }
    },
    "max_batch_size": 1024,
    "input": [
        {
            "name": "CLASS_LOGITS",
            "data_type": "TYPE_FP32",
            "format": "FORMAT_NONE",
            "dims": [
                -1,
                257
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        },
        {
            "name": "END_FLAG",
            "data_type": "TYPE_UINT32",
            "format": "FORMAT_NONE",
            "dims": [
                1
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        },
        {
            "name": "SEGMENTS_START_END",
            "data_type": "TYPE_FP32",
            "format": "FORMAT_NONE",
            "dims": [
                -1,
                2
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        },
        {
            "name": "CUSTOM_CONFIGURATION",
            "data_type": "TYPE_STRING",
            "format": "FORMAT_NONE",
            "dims": [
                -1,
                2
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        }
    ],
    "output": [
        {
            "name": "FINAL_TRANSCRIPTS",
            "data_type": "TYPE_STRING",
            "dims": [
                -1
            ],
            "label_filename": "",
            "is_shape_tensor": false
        },
        {
            "name": "FINAL_TRANSCRIPTS_SCORE",
            "data_type": "TYPE_FP32",
            "dims": [
                -1
            ],
            "label_filename": "",
            "is_shape_tensor": false
        },
        {
            "name": "FINAL_WORDS_START_END",
            "data_type": "TYPE_INT32",
            "dims": [
                -1,
                2
            ],
            "label_filename": "",
            "is_shape_tensor": false
        },
        {
            "name": "PARTIAL_TRANSCRIPTS",
            "data_type": "TYPE_STRING",
            "dims": [
                -1
            ],
            "label_filename": "",
            "is_shape_tensor": false
        },
        {
            "name": "PARTIAL_TRANSCRIPTS_STABILITY",
            "data_type": "TYPE_FP32",
            "dims": [
                -1
            ],
            "label_filename": "",
            "is_shape_tensor": false
        },
        {
            "name": "PARTIAL_WORDS_START_END",
            "data_type": "TYPE_INT32",
            "dims": [
                -1,
                2
            ],
            "label_filename": "",
            "is_shape_tensor": false
        }
    ],
    "batch_input": [],
    "batch_output": [],
    "optimization": {
        "graph": {
            "level": 0
        },
        "priority": "PRIORITY_DEFAULT",
        "cuda": {
            "graphs": false,
            "busy_wait_events": false,
            "graph_spec": [],
            "output_copy_stream": true
        },
        "input_pinned_memory": {
            "enable": true
        },
        "output_pinned_memory": {
            "enable": true
        },
        "gather_kernel_buffer_threshold": 0,
        "eager_batching": false
    },
    "sequence_batching": {
        "oldest": {
            "max_candidate_sequences": 1024,
            "preferred_batch_size": [
                32,
                64
            ],
            "max_queue_delay_microseconds": 1000
        },
        "max_sequence_idle_microseconds": 60000000,
        "control_input": [
            {
                "name": "START",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_START",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            },
            {
                "name": "READY",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_READY",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            },
            {
                "name": "END",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_END",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            },
            {
                "name": "CORRID",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_CORRID",
                        "int32_false_true": [],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_UINT64"
                    }
                ]
            }
        ],
        "state": []
    },
    "instance_group": [
        {
            "name": "conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming_0",
            "kind": "KIND_CPU",
            "count": 1,
            "gpus": [],
            "secondary_devices": [],
            "profile": [],
            "passive": false,
            "host_policy": ""
        }
    ],
    "default_model_filename": "",
    "cc_model_filenames": {},
    "metric_tags": {},
    "parameters": {
        "right_padding_size": {
            "string_value": "1.92"
        },
        "beam_size_token": {
            "string_value": "16"
        },
        "sil_token": {
            "string_value": "▁"
        },
        "num_tokenization": {
            "string_value": "1"
        },
        "beam_threshold": {
            "string_value": "20.0"
        },
        "tokenizer_model": {
            "string_value": "/data/models/conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming/1/8b8f095152034e98b24ab33726708bd0_tokenizer.model"
        },
        "language_model_file": {
            "string_value": "/data/models/conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming/1/en_4.0.bin"
        },
        "max_execution_batch_size": {
            "string_value": "1024"
        },
        "forerunner_use_lm": {
            "string_value": "true"
        },
        "forerunner_beam_size_token": {
            "string_value": "8"
        },
        "forerunner_beam_threshold": {
            "string_value": "10.0"
        },
        "asr_model_delay": {
            "string_value": "-1"
        },
        "decoder_num_worker_threads": {
            "string_value": "-1"
        },
        "word_insertion_score": {
            "string_value": "1.0"
        },
        "unk_token": {
            "string_value": "<unk>"
        },
        "left_padding_size": {
            "string_value": "1.92"
        },
        "set_default_index_to_unk_token": {
            "string_value": "False"
        },
        "decoder_type": {
            "string_value": "flashlight"
        },
        "forerunner_beam_size": {
            "string_value": "8"
        },
        "unk_score": {
            "string_value": "-inf"
        },
        "max_supported_transcripts": {
            "string_value": "1"
        },
        "chunk_size": {
            "string_value": "0.16"
        },
        "lexicon_file": {
            "string_value": "/data/models/conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming/1/lexicon.txt"
        },
        "smearing_mode": {
            "string_value": "max"
        },
        "log_add": {
            "string_value": "True"
        },
        "blank_token": {
            "string_value": "#"
        },
        "lm_weight": {
            "string_value": "0.8"
        },
        "vocab_file": {
            "string_value": "/data/models/conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming/1/riva_decoder_vocabulary.txt"
        },
        "ms_per_timestep": {
            "string_value": "40"
        },
        "streaming": {
            "string_value": "True"
        },
        "use_subword": {
            "string_value": "True"
        },
        "beam_size": {
            "string_value": "32"
        }
    },
    "model_warmup": [],
    "model_transaction_policy": {
        "decoupled": false
    }
}
I0824 23:02:04.616184 101 vad_library.cc:18] TRITONBACKEND_ModelInitialize: conformer-en-US-asr-streaming-voice-activity-detector-ctc-streaming (version 1)
W0824 23:02:04.616688   115 parameter_parser.cc:120] Parameter max_execution_batch_size could not be set from parameters
W0824 23:02:04.616758   115 parameter_parser.cc:121] Default value will be used
W0824 23:02:04.616823   115 parameter_parser.cc:120] Parameter max_execution_batch_size could not be set from parameters
W0824 23:02:04.616858   115 parameter_parser.cc:121] Default value will be used
I0824 23:02:04.617214 101 backend_model.cc:255] model configuration:
{
    "name": "conformer-en-US-asr-streaming-voice-activity-detector-ctc-streaming",
    "platform": "",
    "backend": "riva_asr_vad",
    "version_policy": {
        "latest": {
            "num_versions": 1
        }
    },
    "max_batch_size": 2048,
    "input": [
        {
            "name": "CLASS_LOGITS",
            "data_type": "TYPE_FP32",
            "format": "FORMAT_NONE",
            "dims": [
                -1,
                257
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        }
    ],
    "output": [
        {
            "name": "SEGMENTS_START_END",
            "data_type": "TYPE_FP32",
            "dims": [
                -1,
                2
            ],
            "label_filename": "",
            "is_shape_tensor": false
        }
    ],
    "batch_input": [],
    "batch_output": [],
    "optimization": {
        "graph": {
            "level": 0
        },
        "priority": "PRIORITY_DEFAULT",
        "cuda": {
            "graphs": false,
            "busy_wait_events": false,
            "graph_spec": [],
            "output_copy_stream": true
        },
        "input_pinned_memory": {
            "enable": true
        },
        "output_pinned_memory": {
            "enable": true
        },
        "gather_kernel_buffer_threshold": 0,
        "eager_batching": false
    },
    "sequence_batching": {
        "max_sequence_idle_microseconds": 60000000,
        "control_input": [
            {
                "name": "START",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_START",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            },
            {
                "name": "READY",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_READY",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            }
        ],
        "state": []
    },
    "instance_group": [
        {
            "name": "conformer-en-US-asr-streaming-voice-activity-detector-ctc-streaming_0",
            "kind": "KIND_CPU",
            "count": 1,
            "gpus": [],
            "secondary_devices": [],
            "profile": [],
            "passive": false,
            "host_policy": ""
        }
    ],
    "default_model_filename": "",
    "cc_model_filenames": {},
    "metric_tags": {},
    "parameters": {
        "vad_stop_th": {
            "string_value": "0.98"
        },
        "vad_start_th": {
            "string_value": "0.2"
        },
        "vad_type": {
            "string_value": "ctc-vad"
        },
        "vocab_file": {
            "string_value": "/data/models/conformer-en-US-asr-streaming-voice-activity-detector-ctc-streaming/1/riva_decoder_vocabulary.txt"
        },
        "ms_per_timestep": {
            "string_value": "40"
        },
        "residue_blanks_at_start": {
            "string_value": "-2"
        },
        "use_subword": {
            "string_value": "True"
        },
        "streaming": {
            "string_value": "True"
        },
        "residue_blanks_at_end": {
            "string_value": "0"
        },
        "vad_stop_history": {
            "string_value": "800"
        },
        "vad_start_history": {
            "string_value": "200"
        },
        "chunk_size": {
            "string_value": "0.16"
        }
    },
    "model_warmup": [],
    "model_transaction_policy": {
        "decoupled": false
    }
}
I0824 23:02:04.625366 101 feature-extractor.cc:399] TRITONBACKEND_ModelInitialize: conformer-en-US-asr-streaming-feature-extractor-streaming (version 1)
W0824 23:02:04.626096   114 parameter_parser.cc:120] Parameter is_dither_seed_random could not be set from parameters
W0824 23:02:04.626158   114 parameter_parser.cc:121] Default value will be used
W0824 23:02:04.626210   114 parameter_parser.cc:120] Parameter max_batch_size could not be set from parameters
W0824 23:02:04.626268   114 parameter_parser.cc:121] Default value will be used
W0824 23:02:04.626320   114 parameter_parser.cc:120] Parameter max_sequence_idle_microseconds could not be set from parameters
W0824 23:02:04.626374   114 parameter_parser.cc:121] Default value will be used
W0824 23:02:04.626410   114 parameter_parser.cc:120] Parameter preemph_coeff could not be set from parameters
W0824 23:02:04.626468   114 parameter_parser.cc:121] Default value will be used
I0824 23:02:04.655122 101 backend_model.cc:255] model configuration:
{
    "name": "conformer-en-US-asr-streaming-feature-extractor-streaming",
    "platform": "",
    "backend": "riva_asr_features",
    "version_policy": {
        "latest": {
            "num_versions": 1
        }
    },
    "max_batch_size": 1024,
    "input": [
        {
            "name": "AUDIO_SIGNAL",
            "data_type": "TYPE_FP32",
            "format": "FORMAT_NONE",
            "dims": [
                -1
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        },
        {
            "name": "SAMPLE_RATE",
            "data_type": "TYPE_UINT32",
            "format": "FORMAT_NONE",
            "dims": [
                1
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        }
    ],
    "output": [
        {
            "name": "AUDIO_FEATURES",
            "data_type": "TYPE_FP32",
            "dims": [
                80,
                -1
            ],
            "label_filename": "",
            "is_shape_tensor": false
        },
        {
            "name": "AUDIO_PROCESSED",
            "data_type": "TYPE_FP32",
            "dims": [
                1
            ],
            "label_filename": "",
            "is_shape_tensor": false
        }
    ],
    "batch_input": [],
    "batch_output": [],
    "optimization": {
        "graph": {
            "level": 0
        },
        "priority": "PRIORITY_DEFAULT",
        "cuda": {
            "graphs": false,
            "busy_wait_events": false,
            "graph_spec": [],
            "output_copy_stream": true
        },
        "input_pinned_memory": {
            "enable": true
        },
        "output_pinned_memory": {
            "enable": true
        },
        "gather_kernel_buffer_threshold": 0,
        "eager_batching": false
    },
    "sequence_batching": {
        "oldest": {
            "max_candidate_sequences": 1024,
            "preferred_batch_size": [
                256,
                512
            ],
            "max_queue_delay_microseconds": 1000
        },
        "max_sequence_idle_microseconds": 60000000,
        "control_input": [
            {
                "name": "START",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_START",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            },
            {
                "name": "READY",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_READY",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            },
            {
                "name": "END",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_END",
                        "int32_false_true": [
                            0,
                            1
                        ],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_INVALID"
                    }
                ]
            },
            {
                "name": "CORRID",
                "control": [
                    {
                        "kind": "CONTROL_SEQUENCE_CORRID",
                        "int32_false_true": [],
                        "fp32_false_true": [],
                        "bool_false_true": [],
                        "data_type": "TYPE_UINT64"
                    }
                ]
            }
        ],
        "state": []
    },
    "instance_group": [
        {
            "name": "conformer-en-US-asr-streaming-feature-extractor-streaming_0",
            "kind": "KIND_GPU",
            "count": 1,
            "gpus": [
                0
            ],
            "secondary_devices": [],
            "profile": [],
            "passive": false,
            "host_policy": ""
        }
    ],
    "default_model_filename": "",
    "cc_model_filenames": {},
    "metric_tags": {},
    "parameters": {
        "window_stride": {
            "string_value": "0.01"
        },
        "window_size": {
            "string_value": "0.025"
        },
        "num_features": {
            "string_value": "80"
        },
        "streaming": {
            "string_value": "True"
        },
        "left_padding_size": {
            "string_value": "1.92"
        },
        "stddev_floor": {
            "string_value": "1e-05"
        },
        "transpose": {
            "string_value": "False"
        },
        "right_padding_size": {
            "string_value": "1.92"
        },
        "gain": {
            "string_value": "1.0"
        },
        "use_utterance_norm_params": {
            "string_value": "False"
        },
        "precalc_norm_time_steps": {
            "string_value": "0"
        },
        "precalc_norm_params": {
            "string_value": "False"
        },
        "dither": {
            "string_value": "1e-05"
        },
        "norm_per_feature": {
            "string_value": "True"
        },
        "mean": {
            "string_value": "-11.4412,  -9.9334,  -9.1292,  -9.0365,  -9.2804,  -9.5643,  -9.7342, -9.6925,  -9.6333,  -9.2808,  -9.1887,  -9.1422,  -9.1397,  -9.2028, -9.2749,  -9.4776,  -9.9185, -10.1557, -10.3800, -10.5067, -10.3190, -10.4728, -10.5529, -10.6402, -10.6440, -10.5113, -10.7395, -10.7870, -10.6074, -10.5033, -10.8278, -10.6384, -10.8481, -10.6875, -10.5454, -10.4747, -10.5165, -10.4930, -10.3413, -10.3472, -10.3735, -10.6830, -10.8813, -10.6338, -10.3856, -10.7727, -10.8957, -10.8068, -10.7373, -10.6108, -10.3405, -10.2889, -10.3922, -10.4946, -10.3367, -10.4164, -10.9949, -10.7196, -10.3971, -10.1734,  -9.9257,  -9.6557,  -9.1761, -9.6653,  -9.7876,  -9.7230,  -9.7792,  -9.7056,  -9.2702,  -9.4650, -9.2755,  -9.1369,  -9.1174,  -8.9197,  -8.5394,  -8.2614,  -8.1353, -8.1422,  -8.3430,  -8.6655"
        },
        "stddev": {
            "string_value": "2.2668, 3.1642, 3.7079, 3.7642, 3.5349, 3.5901, 3.7640, 3.8424, 4.0145, 4.1475, 4.0457, 3.9048, 3.7709, 3.6117, 3.3188, 3.1489, 3.0615, 3.0362, 2.9929, 3.0500, 3.0341, 3.0484, 3.0103, 2.9474, 2.9128, 2.8669, 2.8332, 2.9411, 3.0378, 3.0712, 3.0190, 2.9992, 3.0124, 3.0024, 3.0275, 3.0870, 3.0656, 3.0142, 3.0493, 3.1373, 3.1135, 3.0675, 2.8828, 2.7018, 2.6296, 2.8826, 2.9325, 2.9288, 2.9271, 2.9890, 3.0137, 2.9855, 3.0839, 2.9319, 2.3512, 2.3795, 2.6191, 2.7555, 2.9326, 2.9931, 3.1543, 3.0855, 2.6820, 3.0566, 3.1272, 3.1663, 3.1836, 3.0018, 2.9089, 3.1727, 3.1626, 3.1086, 2.9804, 3.1107, 3.2998, 3.3697, 3.3716, 3.2487, 3.1597, 3.1181"
        },
        "chunk_size": {
            "string_value": "0.16"
        },
        "max_execution_batch_size": {
            "string_value": "1024"
        },
        "sample_rate": {
            "string_value": "16000"
        }
    },
    "model_warmup": [],
    "model_transaction_policy": {
        "decoupled": false
    }
}
I0824 23:02:04.655913 101 feature-extractor.cc:401] TRITONBACKEND_ModelInstanceInitialize: conformer-en-US-asr-offline-feature-extractor-streaming-offline_0 (device 0)
  > Riva waiting for Triton server to load all models...retrying in 1 second
  > Riva waiting for Triton server to load all models...retrying in 1 second
  > Riva waiting for Triton server to load all models...retrying in 1 second
  > Riva waiting for Triton server to load all models...retrying in 1 second
  > Riva waiting for Triton server to load all models...retrying in 1 second
I0824 23:02:09.718234 101 ctc-decoder-library.cc:23] TRITONBACKEND_ModelInstanceInitialize: conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming_0 (device 0)
I0824 23:02:09.718793 101 model_repository_manager.cc:1231] successfully loaded 'conformer-en-US-asr-offline-feature-extractor-streaming-offline' version 1
  > Riva waiting for Triton server to load all models...retrying in 1 second
  > Riva waiting for Triton server to load all models...retrying in 1 second
I0824 23:02:11.700796   110 ctc-decoder.cc:171] Beam Decoder initialized successfully!
I0824 23:02:11.701091 101 vad_library.cc:21] TRITONBACKEND_ModelInstanceInitialize: conformer-en-US-asr-streaming-voice-activity-detector-ctc-streaming_0 (device 0)
I0824 23:02:11.707552 101 model_repository_manager.cc:1231] successfully loaded 'conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming' version 1
I0824 23:02:11.735048 101 vad_library.cc:21] TRITONBACKEND_ModelInstanceInitialize: conformer-en-US-asr-offline-voice-activity-detector-ctc-streaming-offline_0 (device 0)
I0824 23:02:11.744431 101 model_repository_manager.cc:1231] successfully loaded 'conformer-en-US-asr-streaming-voice-activity-detector-ctc-streaming' version 1
I0824 23:02:11.776780 101 model_repository_manager.cc:1231] successfully loaded 'conformer-en-US-asr-offline-voice-activity-detector-ctc-streaming-offline' version 1
I0824 23:02:11.804831 101 pipeline_library.cc:19] TRITONBACKEND_ModelInitialize: riva-punctuation-en-US (version 1)
WARNING: Logging before InitGoogleLogging() is written to STDERR
W0824 23:02:11.805441   116 parameter_parser.cc:120] Parameter bos could not be set from parameters
W0824 23:02:11.805532   116 parameter_parser.cc:121] Default value will be used
W0824 23:02:11.805596   116 parameter_parser.cc:120] Parameter dropout_prob could not be set from parameters
W0824 23:02:11.805655   116 parameter_parser.cc:121] Default value will be used
W0824 23:02:11.805723   116 parameter_parser.cc:120] Parameter eos could not be set from parameters
W0824 23:02:11.805778   116 parameter_parser.cc:121] Default value will be used
W0824 23:02:11.805819   116 parameter_parser.cc:120] Parameter reverse could not be set from parameters
W0824 23:02:11.805871   116 parameter_parser.cc:121] Default value will be used
W0824 23:02:11.805956   116 parameter_parser.cc:120] Parameter bos could not be set from parameters
W0824 23:02:11.805999   116 parameter_parser.cc:121] Default value will be used
W0824 23:02:11.806033   116 parameter_parser.cc:120] Parameter doc_stride could not be set from parameters
W0824 23:02:11.806087   116 parameter_parser.cc:121] Default value will be used
W0824 23:02:11.806121   116 parameter_parser.cc:120] Parameter dropout_prob could not be set from parameters
W0824 23:02:11.806174   116 parameter_parser.cc:121] Default value will be used
W0824 23:02:11.806207   116 parameter_parser.cc:120] Parameter eos could not be set from parameters
W0824 23:02:11.806260   116 parameter_parser.cc:121] Default value will be used
W0824 23:02:11.806295   116 parameter_parser.cc:120] Parameter margin could not be set from parameters
W0824 23:02:11.806349   116 parameter_parser.cc:121] Default value will be used
W0824 23:02:11.806382   116 parameter_parser.cc:120] Parameter max_batch_size could not be set from parameters
W0824 23:02:11.806435   116 parameter_parser.cc:121] Default value will be used
W0824 23:02:11.806469   116 parameter_parser.cc:120] Parameter max_query_length could not be set from parameters
W0824 23:02:11.806522   116 parameter_parser.cc:121] Default value will be used
W0824 23:02:11.806555   116 parameter_parser.cc:120] Parameter max_seq_length could not be set from parameters
W0824 23:02:11.806608   116 parameter_parser.cc:121] Default value will be used
W0824 23:02:11.806644   116 parameter_parser.cc:120] Parameter reverse could not be set from parameters
W0824 23:02:11.806695   116 parameter_parser.cc:121] Default value will be used
W0824 23:02:11.806736   116 parameter_parser.cc:120] Parameter step could not be set from parameters
W0824 23:02:11.806787   116 parameter_parser.cc:121] Default value will be used
W0824 23:02:11.806828   116 parameter_parser.cc:120] Parameter task could not be set from parameters
W0824 23:02:11.806879   116 parameter_parser.cc:121] Default value will be used
I0824 23:02:11.806977 101 backend_model.cc:255] model configuration:
{
    "name": "riva-punctuation-en-US",
    "platform": "",
    "backend": "riva_nlp_pipeline",
    "version_policy": {
        "latest": {
            "num_versions": 1
        }
    },
    "max_batch_size": 8,
    "input": [
        {
            "name": "PIPELINE_INPUT",
            "data_type": "TYPE_STRING",
            "format": "FORMAT_NONE",
            "dims": [
                1
            ],
            "is_shape_tensor": false,
            "allow_ragged_batch": false,
            "optional": false
        }
    ],
    "output": [
        {
            "name": "PIPELINE_OUTPUT",
            "data_type": "TYPE_STRING",
            "dims": [
                1
            ],
            "label_filename": "",
            "is_shape_tensor": false
        }
    ],
    "batch_input": [],
    "batch_output": [],
    "optimization": {
        "priority": "PRIORITY_DEFAULT",
        "input_pinned_memory": {
            "enable": true
        },
        "output_pinned_memory": {
            "enable": true
        },
        "gather_kernel_buffer_threshold": 0,
        "eager_batching": false
    },
    "instance_group": [
        {
            "name": "riva-punctuation-en-US_0",
            "kind": "KIND_CPU",
            "count": 1,
            "gpus": [],
            "secondary_devices": [],
            "profile": [],
            "passive": false,
            "host_policy": ""
        }
    ],
    "default_model_filename": "",
    "cc_model_filenames": {},
    "metric_tags": {},
    "parameters": {
        "to_lower": {
            "string_value": "true"
        },
        "pipeline_type": {
            "string_value": "punctuation"
        },
        "capitalization_mapping_path": {
            "string_value": "/data/models/riva-punctuation-en-US/1/capit_label_ids.csv"
        },
        "eos_token": {
            "string_value": "[SEP]"
        },
        "load_model": {
            "string_value": "false"
        },
        "attn_mask_tensor_name": {
            "string_value": "input_mask"
        },
        "token_type_tensor_name": {
            "string_value": "segment_ids"
        },
        "punct_logits_tensor_name": {
            "string_value": "punct_token_logits"
        },
        "language_code": {
            "string_value": "en-US"
        },
        "tokenizer": {
            "string_value": "wordpiece"
        },
        "delimiter": {
            "string_value": " "
        },
        "input_ids_tensor_name": {
            "string_value": "input_ids"
        },
        "model_name": {
            "string_value": "riva-trt-riva-punctuation-en-US-nn-bert-base-uncased"
        },
        "pad_chars_with_spaces": {
            "string_value": "False"
        },
        "remove_spaces": {
            "string_value": "False"
        },
        "tokenizer_to_lower": {
            "string_value": "true"
        },
        "model_family": {
            "string_value": "riva"
        },
        "unk_token": {
            "string_value": "[UNK]"
        },
        "vocab": {
            "string_value": "/data/models/riva-punctuation-en-US/1/tokenizer.vocab_file"
        },
        "bos_token": {
            "string_value": "[CLS]"
        },
        "capit_logits_tensor_name": {
            "string_value": "capit_token_logits"
        },
        "punctuation_mapping_path": {
            "string_value": "/data/models/riva-punctuation-en-US/1/punct_label_ids.csv"
        },
        "model_api": {
            "string_value": "/nvidia.riva.nlp.RivaLanguageUnderstanding/PunctuateText"
        }
    },
    "model_warmup": []
}
I0824 23:02:11.807636 101 pipeline_library.cc:22] TRITONBACKEND_ModelInstanceInitialize: riva-punctuation-en-US_0 (device 0)
I0824 23:02:11.818480 101 feature-extractor.cc:401] TRITONBACKEND_ModelInstanceInitialize: conformer-en-US-asr-streaming-feature-extractor-streaming_0 (device 0)
I0824 23:02:11.823758 101 model_repository_manager.cc:1231] successfully loaded 'riva-punctuation-en-US' version 1
I0824 23:02:12.121284 101 tensorrt.cc:5294] TRITONBACKEND_Initialize: tensorrt
I0824 23:02:12.121475 101 tensorrt.cc:5304] Triton TRITONBACKEND API version: 1.9
I0824 23:02:12.121548 101 tensorrt.cc:5310] 'tensorrt' TRITONBACKEND API version: 1.9
I0824 23:02:12.121809 101 tensorrt.cc:5353] backend configuration:
{}
I0824 23:02:12.121942 101 tensorrt.cc:5405] TRITONBACKEND_ModelInitialize: riva-trt-conformer-en-US-asr-offline-am-streaming-offline (version 1)
I0824 23:02:12.122602 101 tensorrt.cc:5454] TRITONBACKEND_ModelInstanceInitialize: riva-trt-conformer-en-US-asr-offline-am-streaming-offline_0 (GPU device 0)
I0824 23:02:12.123533 101 model_repository_manager.cc:1231] successfully loaded 'conformer-en-US-asr-streaming-feature-extractor-streaming' version 1
  > Riva waiting for Triton server to load all models...retrying in 1 second
  > Riva waiting for Triton server to load all models...retrying in 1 second
I0824 23:02:13.982613 101 logging.cc:49] [MemUsageChange] Init CUDA: CPU +417, GPU +0, now: CPU 2003, GPU 5996 (MiB)
  > Riva waiting for Triton server to load all models...retrying in 1 second
I0824 23:02:14.675465 101 logging.cc:49] Loaded engine size: 416 MiB
  > Riva waiting for Triton server to load all models...retrying in 1 second
I0824 23:02:15.997027 101 logging.cc:49] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +8, now: CPU 2951, GPU 6342 (MiB)
I0824 23:02:16.277753 101 logging.cc:49] [MemUsageChange] Init cuDNN: CPU +127, GPU +58, now: CPU 3078, GPU 6400 (MiB)
I0824 23:02:16.282010 101 logging.cc:49] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +330, now: CPU 0, GPU 330 (MiB)
I0824 23:02:16.322536 101 logging.cc:49] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +8, now: CPU 2245, GPU 6392 (MiB)
I0824 23:02:16.323401 101 logging.cc:49] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 2245, GPU 6400 (MiB)
  > Riva waiting for Triton server to load all models...retrying in 1 second
  > Riva waiting for Triton server to load all models...retrying in 1 second
  > Riva waiting for Triton server to load all models...retrying in 1 second
I0824 23:02:19.250465 101 logging.cc:49] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +365, now: CPU 0, GPU 695 (MiB)
  > Riva waiting for Triton server to load all models...retrying in 1 second
  > Riva waiting for Triton server to load all models...retrying in 1 second
  > Riva waiting for Triton server to load all models...retrying in 1 second
I0824 23:02:22.130511 101 tensorrt.cc:1411] Created instance riva-trt-conformer-en-US-asr-offline-am-streaming-offline_0 on GPU 0 with stream priority 0 and optimization profile default[0];
I0824 23:02:22.130794 101 tensorrt.cc:5405] TRITONBACKEND_ModelInitialize: riva-trt-riva-punctuation-en-US-nn-bert-base-uncased (version 1)
I0824 23:02:22.131522 101 tensorrt.cc:5454] TRITONBACKEND_ModelInstanceInitialize: riva-trt-riva-punctuation-en-US-nn-bert-base-uncased_0 (GPU device 0)
I0824 23:02:22.132337 101 logging.cc:49] [MemUsageChange] Init CUDA: CPU +0, GPU +0, now: CPU 3232, GPU 7669 (MiB)
I0824 23:02:22.141030 101 model_repository_manager.cc:1231] successfully loaded 'riva-trt-conformer-en-US-asr-offline-am-streaming-offline' version 1
I0824 23:02:22.553322 101 logging.cc:49] Loaded engine size: 208 MiB
  > Riva waiting for Triton server to load all models...retrying in 1 second
I0824 23:02:22.745298 101 logging.cc:49] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +8, now: CPU 3763, GPU 8011 (MiB)
I0824 23:02:22.746580 101 logging.cc:49] [MemUsageChange] Init cuDNN: CPU +0, GPU +10, now: CPU 3763, GPU 8021 (MiB)
I0824 23:02:22.750318 101 logging.cc:49] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +95, now: CPU 0, GPU 790 (MiB)
I0824 23:02:22.776407 101 logging.cc:49] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +8, now: CPU 3347, GPU 8013 (MiB)
I0824 23:02:22.777337 101 logging.cc:49] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 3347, GPU 8021 (MiB)
E0824 23:02:22.849849 101 logging.cc:43] /home/jenkins/agent/workspace/OSS/OSS_L0_MergeRequest/oss/plugin/common/bertCommon.h (395) - Cuda Error in copyToDevice: 2 (out of memory)
E0824 23:02:22.853534 101 logging.cc:43] std::exception
E0824 23:02:22.855729 101 logging.cc:43] /home/jenkins/agent/workspace/OSS/OSS_L0_MergeRequest/oss/plugin/common/bertCommon.h (395) - Cuda Error in copyToDevice: 2 (out of memory)
E0824 23:02:22.855860 101 logging.cc:43] std::exception
E0824 23:02:22.857959 101 logging.cc:43] /home/jenkins/agent/workspace/OSS/OSS_L0_MergeRequest/oss/plugin/common/bertCommon.h (395) - Cuda Error in copyToDevice: 2 (out of memory)
E0824 23:02:22.858085 101 logging.cc:43] std::exception
E0824 23:02:22.858954 101 logging.cc:43] /home/jenkins/agent/workspace/OSS/OSS_L0_MergeRequest/oss/plugin/common/bertCommon.h (395) - Cuda Error in copyToDevice: 2 (out of memory)
E0824 23:02:22.859080 101 logging.cc:43] std::exception
E0824 23:02:22.860069 101 logging.cc:43] /home/jenkins/agent/workspace/OSS/OSS_L0_MergeRequest/oss/plugin/common/bertCommon.h (395) - Cuda Error in copyToDevice: 2 (out of memory)
E0824 23:02:22.860191 101 logging.cc:43] std::exception
E0824 23:02:22.865334 101 logging.cc:43] 1: [defaultAllocator.cpp::allocate::18] Error Code 1: Cuda Runtime (out of memory)
W0824 23:02:22.865911 101 logging.cc:46] -------------- The current system memory allocations dump as below --------------
[0x7f6b958e70d0]:66463 :GPU per-runner memory in ExecutionContext: at runtime/api/executionContext.cpp: 160 idx: 149 time: 6.14e-07
[0x7f6b95b689d0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 148 time: 3.33e-07
[0x7f6b95b688b0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 147 time: 5.8e-08
[0x7f6b95b65c20]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 146 time: 1.01e-07
[0x7f6b95b65b00]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 145 time: 8.7e-08
[0x7f6b956d11a0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 143 time: 9.1e-08
[0x7f6b956c5100]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 139 time: 6.5e-08
[0x7f6b956ad4f0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 137 time: 6.4e-08
[0x7f6b956a99f0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 135 time: 1.02e-07
[0x7f6b956920d0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 134 time: 1.17e-07
[0x7f6b95691fb0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 133 time: 1.05e-07
[0x7f6b956901c0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 132 time: 2.25e-07
[0x7f6b9568e410]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 131 time: 1.15e-07
[0x7f6b95676950]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 130 time: 9e-08
[0x7f6b95676830]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 129 time: 9.8e-08
[0x7f6b95672590]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 127 time: 6.8e-08
[0x7f68c6c68d00]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 55 time: 1.92e-07
[0x7f68c5182890]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 31 time: 1.08e-07
[0x7f68c6ab5320]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 53 time: 2.61e-07
[0x7f68c66183a0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 50 time: 1.56e-07
[0x7f69073c0130]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 9 time: 2.44e-07
[0x7f68c646a9f0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 48 time: 2.85e-07
[0x7f68c5fcd950]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 44 time: 2.62e-07
[0x7f68c5e202c0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 43 time: 2.87e-07
[0x7f68c4ceea60]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 29 time: 2.64e-07
[0x7f6b95608630]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 114 time: 9.3e-08
[0x7f68c57f4cc0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 37 time: 1.91e-07
[0x7f68c7db9aa0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 67 time: 1.31e-07
[0x7f68c5339410]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 35 time: 2.3e-07
[0x7f6b95674340]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 128 time: 2.17e-07
[0x7f6907853c90]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 11 time: 6.6e-08
[0x7f690722cdd0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 7 time: 1.56e-07
[0x7f68c5983340]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 40 time: 2.62e-07
[0x7f68c6ad3c50]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 52 time: 5.7e-08
[0x7f68c6489320]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 47 time: 9.1e-08
[0x7f68c44e9b20]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 21 time: 8e-08
[0x7f6907ea8940]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 18 time: 2.63e-07
[0x7f6b955d19c0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 105 time: 1.23e-07
[0x7f68c7f47c90]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 70 time: 2.62e-07
[0x7f68c51aa590]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 32 time: 7e-08
[0x7f6b956d12c0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 144 time: 1.24e-07
[0x7f68bca31ec0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 76 time: 1.22e-07
[0x7f6b95604a80]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 111 time: 9.1e-08
[0x7f68c6c68be0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 54 time: 1.27e-07
[0x7f69070b80d0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 5 time: 3.22e-07
[0x7f69070921a0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 4 time: 1.01e-07
[0x7f6b956ad610]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 138 time: 8.2e-08
[0x7f6906c48be0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 3 time: 1.65e-07
[0x7f68c4b5c3c0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 27 time: 6.3e-08
[0x7f68c5e3ebf0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 42 time: 5e-08
[0x7f690787b5a0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 12 time: 8.6e-08
[0x7f6907e9f780]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 16 time: 6.2e-08
[0x7f68c70fcac0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 56 time: 1.09e-07
[0x7f68c44f2ce0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 23 time: 4.81e-07
[0x7f68bc59df90]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 74 time: 1.61e-07
[0x7f68c53392f0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 34 time: 1.37e-07
[0x7f6906c4efe0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 1 time: 1.85e-07
[0x7f6906c48a80]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 2 time: 6.6e-08
[0x7f68c46a09f0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 24 time: 1.34e-07
[0x7f69073c0250]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 10 time: 2.34e-07
[0x7f68c6aac160]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 51 time: 5.9e-08
[0x7f68c5fcda70]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 45 time: 2.19e-07
[0x7f6b955ecfd0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 109 time: 9.8e-08
[0x7f6907094d30]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 6 time: 9.1e-08
[0x7f68c4ceeb80]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 30 time: 3.32e-07
[0x7f69065964b0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 0 time: 1.11e-07
[0x7f68c4b348d0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 26 time: 7.8e-08
[0x7f690785ccc0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 13 time: 2.77e-07
[0x7f68bde12ee0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 95 time: 2.57e-07
[0x7f6b956ab7a0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 136 time: 3.35e-07
[0x7f68c5983220]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 39 time: 1.51e-07
[0x7f68bd07c050]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 81 time: 6.5e-08
[0x7f6907ec7270]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 17 time: 7.9e-08
[0x7f68c6461830]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 46 time: 1.27e-07
[0x7f69072050e0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 8 time: 4.04e-07
[0x7f6907a0a0b0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 14 time: 1.21e-07
[0x7f68c4055c40]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 19 time: 1.6e-07
[0x7f6b95656fe0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 123 time: 7.2e-08
[0x7f68c6618280]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 49 time: 2.62e-07
[0x7f68c57d6390]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 38 time: 3.05e-07
[0x7f68c7d9b170]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 68 time: 3.77e-07
[0x7f68c7f47b70]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 69 time: 2.64e-07
[0x7f6b955b49a0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 100 time: 3.11e-07
[0x7f68c4055d60]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 20 time: 5.4e-07
[0x7f68c4511610]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 22 time: 1.02e-07
[0x7f68c72b2e60]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 60 time: 2.01e-07
[0x7f68c71245b0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 57 time: 5.2e-08
[0x7f68c57cd1d0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 36 time: 8.2e-08
[0x7f68c5e17100]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 41 time: 8.2e-08
[0x7f68c46a0b10]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 25 time: 1.91e-07
[0x7f68c4b3da90]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 28 time: 2.9e-07
[0x7f68bc3e7770]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 71 time: 8.3e-08
[0x7f6b956c6eb0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 140 time: 2.95e-07
[0x7f6b955cdf30]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 103 time: 1.01e-07
[0x7f6b955e9540]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 107 time: 8.1e-08
[0x7f68c72b2d40]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 59 time: 2.93e-07
[0x7f68bdd1a2f0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 93 time: 2.62e-07
[0x7f68c7746c20]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 61 time: 2.55e-07
[0x7f68c78fe200]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 65 time: 2.25e-07
[0x7f68c776e920]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 62 time: 4.6e-08
[0x7f68c774fff0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 63 time: 2.84e-07
[0x7f6b953399c0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 98 time: 4.51e-07
[0x7f6907a0a1d0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 15 time: 2.16e-07
[0x7f68c78fe0e0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 64 time: 2.62e-07
[0x7f68bc40f260]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 72 time: 8.2e-08
[0x7f68c7105c80]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 58 time: 2.8e-07
[0x7f68bc59e0b0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 75 time: 1.21e-07
[0x7f68bca59bc0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 77 time: 7.8e-08
[0x7f68bca3b290]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 78 time: 2.85e-07
[0x7f6b956c8d90]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 142 time: 1.05e-07
[0x7f68bd2329a0]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 85 time: 2.48e-07
[0x7f6b955b6950]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 102 time: 1.77e-07
[0x7f68bcbe8120]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 79 time: 1.49e-07
[0x7f68bd6cf970]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 88 time: 2.6e-07
[0x7f68bcbe8240]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 80 time: 1.81e-07
[0x7f6b9563f5d0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 121 time: 7.5e-08
[0x7f68bd0a3d50]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 82 time: 4.4e-08
[0x7f68bd87d320]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 90 time: 2.08e-07
[0x7f68bd085420]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 83 time: 2.28e-07
[0x7f6b9563ba00]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 119 time: 8.5e-08
[0x7f6b956c8c70]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 141 time: 9.7e-08
[0x7f68bd232880]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 84 time: 2.64e-07
[0x7f6b955b6830]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 101 time: 2.57e-07
[0x7f6b9563f6f0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 122 time: 8.4e-08
[0x7f68c518bc60]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 33 time: 2.96e-07
[0x7f68bd6c67b0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 86 time: 6.6e-08
[0x7f68bd6ee2a0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 87 time: 4.5e-08
[0x7f68bd87d200]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 89 time: 1.45e-07
[0x7f68bdd11130]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 91 time: 7.7e-08
[0x7f6b95606840]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 112 time: 1.98e-07
[0x7f6b956219f0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 116 time: 3.61e-07
[0x7f6b956239b0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 117 time: 8.3e-08
[0x7f68bc3f0930]:2527 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 73 time: 3.13e-07
[0x7f68bdd38c20]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 92 time: 8.3e-08
[0x7f6b95608510]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 113 time: 8.3e-08
[0x7f68bddccac0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 94 time: 8.5e-08
[0x7f68b0c8b600]:224383 :GPU per-runner memory in ExecutionContext: at runtime/api/executionContext.cpp: 160 idx: 96 time: 4.18e-07
[0x7f6b95339920]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 97 time: 2.8e-07
[0x7f6b955ce050]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 104 time: 2.16e-07
[0x7f6b955d1ae0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 106 time: 1.46e-07
[0x7f6b955b2d70]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 99 time: 1.35e-07
[0x7f6b955eb0f0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 108 time: 3.39e-07
[0x7f6b955ed0f0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 110 time: 1.09e-07
[0x7f6b9561fe80]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 115 time: 9.7e-08
[0x7f6b95623ad0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 118 time: 1.05e-07
[0x7f68c7d91fb0]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 66 time: 1.97e-07
[0x7f6b9563cfa0]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 120 time: 3.47e-07
[0x7f6b95658d90]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 124 time: 2.57e-07
[0x7f6b9565aa10]:4 : in internalAllocate: at runtime/common/weightsPtr.cpp: 100 idx: 125 time: 6.5e-08
[0x7f6b9565ab30]:2303 :Safe deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 348 idx: 126 time: 8e-08
-------------- The current device memory allocations dump as below --------------
[0x101ca000000]:99257344 :GpuGlob deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 361 idx: 3 time: 0.000567058
[0]:99257344 :GPU per-runner memory in ExecutionContext: at runtime/api/executionContext.cpp: 163 idx: 4 time: 0.00508422
[0x10176000000]:349485056 :GPU context memory in ExecutionContext: at runtime/api/executionContext.cpp: 214 idx: 2 time: 0.00049535
[0x10174000000]:33548288 :GPU per-runner memory in ExecutionContext: at runtime/api/executionContext.cpp: 163 idx: 1 time: 0.000300524
[0x1006ce00000]:346586128 :GpuGlob deserialization in load: at runtime/deserialization/safeDeserialize.cpp: 361 idx: 0 time: 0.00076128
W0824 23:02:22.866533 101 logging.cc:46] Requested amount of GPU memory (99257344 bytes) could not be allocated. There may not be enough free memory for allocation to succeed.
E0824 23:02:22.876246 101 logging.cc:43] 2: [executionContext.cpp::ExecutionContext::163] Error Code 2: OutOfMemory (no further information)
I0824 23:02:22.876372 101 tensorrt.cc:5492] TRITONBACKEND_ModelInstanceFinalize: delete instance state
I0824 23:02:22.876502 101 tensorrt.cc:5431] TRITONBACKEND_ModelFinalize: delete model state
E0824 23:02:22.876614 101 model_repository_manager.cc:1234] failed to load 'riva-trt-riva-punctuation-en-US-nn-bert-base-uncased' version 1: Internal: unable to create TensorRT context
I0824 23:02:22.877260 101 model_repository_manager.cc:1077] loading: conformer-en-US-asr-offline:1
I0824 23:02:22.977592 101 model_repository_manager.cc:1231] successfully loaded 'conformer-en-US-asr-offline' version 1
I0824 23:02:22.977761 101 server.cc:549] 
+------------------+------+
| Repository Agent | Path |
+------------------+------+
+------------------+------+

I0824 23:02:22.977914 101 server.cc:576] 
+-------------------+-----------------------------------------------------------------------------+--------+
| Backend           | Path                                                                        | Config |
+-------------------+-----------------------------------------------------------------------------+--------+
| onnxruntime       | /opt/tritonserver/backends/onnxruntime/libtriton_onnxruntime.so             | {}     |
| riva_asr_decoder  | /opt/tritonserver/backends/riva_asr_decoder/libtriton_riva_asr_decoder.so   | {}     |
| tensorrt          | /opt/tritonserver/backends/tensorrt/libtriton_tensorrt.so                   | {}     |
| riva_asr_vad      | /opt/tritonserver/backends/riva_asr_vad/libtriton_riva_asr_vad.so           | {}     |
| riva_asr_features | /opt/tritonserver/backends/riva_asr_features/libtriton_riva_asr_features.so | {}     |
| riva_nlp_pipeline | /opt/tritonserver/backends/riva_nlp_pipeline/libtriton_riva_nlp_pipeline.so | {}     |
+-------------------+-----------------------------------------------------------------------------+--------+

I0824 23:02:22.978121 101 server.cc:619] 
+---------------------------------------------------------------------------+---------+----------------------------------------------------------+
| Model                                                                     | Version | Status                                                   |
+---------------------------------------------------------------------------+---------+----------------------------------------------------------+
| conformer-en-US-asr-offline                                               | 1       | READY                                                    |
| conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline             | 1       | READY                                                    |
| conformer-en-US-asr-offline-feature-extractor-streaming-offline           | 1       | READY                                                    |
| conformer-en-US-asr-offline-voice-activity-detector-ctc-streaming-offline | 1       | READY                                                    |
| conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming                   | 1       | READY                                                    |
| conformer-en-US-asr-streaming-feature-extractor-streaming                 | 1       | READY                                                    |
| conformer-en-US-asr-streaming-voice-activity-detector-ctc-streaming       | 1       | READY                                                    |
| riva-punctuation-en-US                                                    | 1       | READY                                                    |
| riva-trt-conformer-en-US-asr-offline-am-streaming-offline                 | 1       | READY                                                    |
| riva-trt-riva-punctuation-en-US-nn-bert-base-uncased                      | 1       | UNAVAILABLE: Internal: unable to create TensorRT context |
+---------------------------------------------------------------------------+---------+----------------------------------------------------------+

I0824 23:02:23.000316 101 metrics.cc:650] Collecting metrics for GPU 0: GRID A100D-8C
I0824 23:02:23.000630 101 tritonserver.cc:2123] 
+----------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Option                           | Value                                                                                                                                                                                        |
+----------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| server_id                        | triton                                                                                                                                                                                       |
| server_version                   | 2.21.0                                                                                                                                                                                       |
| server_extensions                | classification sequence model_repository model_repository(unload_dependents) schedule_policy model_configuration system_shared_memory cuda_shared_memory binary_tensor_data statistics trace |
| model_repository_path[0]         | /data/models                                                                                                                                                                                 |
| model_control_mode               | MODE_NONE                                                                                                                                                                                    |
| strict_model_config              | 1                                                                                                                                                                                            |
| rate_limit                       | OFF                                                                                                                                                                                          |
| pinned_memory_pool_byte_size     | 268435456                                                                                                                                                                                    |
| cuda_memory_pool_byte_size{0}    | 1000000000                                                                                                                                                                                   |
| response_cache_byte_size         | 0                                                                                                                                                                                            |
| min_supported_compute_capability | 6.0                                                                                                                                                                                          |
| strict_readiness                 | 1                                                                                                                                                                                            |
| exit_timeout                     | 30                                                                                                                                                                                           |
+----------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

I0824 23:02:23.000821 101 server.cc:250] Waiting for in-flight requests to complete.
I0824 23:02:23.000896 101 server.cc:266] Timeout 30: Found 0 model versions that have in-flight inferences
I0824 23:02:23.000980 101 model_repository_manager.cc:1109] unloading: conformer-en-US-asr-streaming-feature-extractor-streaming:1
I0824 23:02:23.001105 101 model_repository_manager.cc:1109] unloading: conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming:1
I0824 23:02:23.001222 101 model_repository_manager.cc:1109] unloading: riva-trt-conformer-en-US-asr-offline-am-streaming-offline:1
I0824 23:02:23.001333 101 model_repository_manager.cc:1109] unloading: riva-punctuation-en-US:1
I0824 23:02:23.001446 101 model_repository_manager.cc:1109] unloading: conformer-en-US-asr-offline-voice-activity-detector-ctc-streaming-offline:1
I0824 23:02:23.001554 101 model_repository_manager.cc:1109] unloading: conformer-en-US-asr-offline-feature-extractor-streaming-offline:1
I0824 23:02:23.001662 101 model_repository_manager.cc:1109] unloading: conformer-en-US-asr-streaming-voice-activity-detector-ctc-streaming:1
I0824 23:02:23.001782 101 model_repository_manager.cc:1109] unloading: conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline:1
I0824 23:02:23.001894 101 model_repository_manager.cc:1109] unloading: conformer-en-US-asr-offline:1
I0824 23:02:23.002001 101 server.cc:281] All models are stopped, unloading models
I0824 23:02:23.002072 101 server.cc:288] Timeout 30: Found 9 live models and 0 in-flight non-inference requests
I0824 23:02:23.002282 101 vad_library.cc:24] TRITONBACKEND_ModelInstanceFinalize: delete instance state
I0824 23:02:23.002606 101 ctc-decoder-library.cc:25] TRITONBACKEND_ModelInstanceFinalize: delete instance state
I0824 23:02:23.003026 101 feature-extractor.cc:403] TRITONBACKEND_ModelInstanceFinalize: delete instance state
I0824 23:02:23.002490 101 model_repository_manager.cc:1214] successfully unloaded 'conformer-en-US-asr-offline' version 1
I0824 23:02:23.007804 101 vad_library.cc:24] TRITONBACKEND_ModelInstanceFinalize: delete instance state
I0824 23:02:23.013304 101 pipeline_library.cc:24] TRITONBACKEND_ModelInstanceFinalize: delete instance state
I0824 23:02:23.014370 101 tensorrt.cc:5492] TRITONBACKEND_ModelInstanceFinalize: delete instance state
I0824 23:02:23.015773 101 ctc-decoder-library.cc:25] TRITONBACKEND_ModelInstanceFinalize: delete instance state
I0824 23:02:23.022082 101 pipeline_library.cc:21] TRITONBACKEND_ModelFinalize: delete model stateI0824 23:02:23.022221 101 feature-extractor.cc:403] TRITONBACKEND_ModelInstanceFinalize: delete instance state

I0824 23:02:23.034687 101 vad_library.cc:20] TRITONBACKEND_ModelFinalize: delete model state
I0824 23:02:23.034938 101 vad_library.cc:20] TRITONBACKEND_ModelFinalize: delete model state
I0824 23:02:23.040116 101 model_repository_manager.cc:1214] successfully unloaded 'conformer-en-US-asr-streaming-voice-activity-detector-ctc-streaming' version 1
I0824 23:02:23.049024 101 model_repository_manager.cc:1214] successfully unloaded 'conformer-en-US-asr-offline-voice-activity-detector-ctc-streaming-offline' version 1
I0824 23:02:23.049226 101 model_repository_manager.cc:1214] successfully unloaded 'riva-punctuation-en-US' version 1
I0824 23:02:23.055651 101 feature-extractor.cc:400] TRITONBACKEND_ModelFinalize: delete model state
I0824 23:02:23.056024 101 model_repository_manager.cc:1214] successfully unloaded 'conformer-en-US-asr-streaming-feature-extractor-streaming' version 1
I0824 23:02:23.086297 101 feature-extractor.cc:400] TRITONBACKEND_ModelFinalize: delete model state
I0824 23:02:23.087447 101 model_repository_manager.cc:1214] successfully unloaded 'conformer-en-US-asr-offline-feature-extractor-streaming-offline' version 1
I0824 23:02:23.466094 101 tensorrt.cc:5431] TRITONBACKEND_ModelFinalize: delete model state
I0824 23:02:23.472491 101 model_repository_manager.cc:1214] successfully unloaded 'riva-trt-conformer-en-US-asr-offline-am-streaming-offline' version 1
  > Riva waiting for Triton server to load all models...retrying in 1 second
I0824 23:02:24.002232 101 server.cc:288] Timeout 29: Found 2 live models and 0 in-flight non-inference requests
W0824 23:02:24.326208 101 metrics.cc:426] Unable to get power limit for GPU 0. Status:Success, value:0.000000
W0824 23:02:24.326418 101 metrics.cc:444] Unable to get power usage for GPU 0. Status:Success, value:0.000000
W0824 23:02:24.326499 101 metrics.cc:468] Unable to get energy consumption for GPU 0. Status:Success, value:0
I0824 23:02:24.326655 101 ctc-decoder-library.cc:22] TRITONBACKEND_ModelFinalize: delete model state
I0824 23:02:24.386914 101 model_repository_manager.cc:1214] successfully unloaded 'conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline' version 1
I0824 23:02:24.455230 101 ctc-decoder-library.cc:22] TRITONBACKEND_ModelFinalize: delete model state
I0824 23:02:24.513075 101 model_repository_manager.cc:1214] successfully unloaded 'conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming' version 1
  > Riva waiting for Triton server to load all models...retrying in 1 second
I0824 23:02:25.002513 101 server.cc:288] Timeout 28: Found 0 live models and 0 in-flight non-inference requests
error: creating server: Internal - failed to load all models
W0824 23:02:25.326667 101 metrics.cc:426] Unable to get power limit for GPU 0. Status:Success, value:0.000000
W0824 23:02:25.326882 101 metrics.cc:444] Unable to get power usage for GPU 0. Status:Success, value:0.000000
W0824 23:02:25.326957 101 metrics.cc:468] Unable to get energy consumption for GPU 0. Status:Success, value:0
  > Riva waiting for Triton server to load all models...retrying in 1 second
W0824 23:02:26.328402 101 metrics.cc:426] Unable to get power limit for GPU 0. Status:Success, value:0.000000
W0824 23:02:26.328612 101 metrics.cc:444] Unable to get power usage for GPU 0. Status:Success, value:0.000000
W0824 23:02:26.328686 101 metrics.cc:468] Unable to get energy consumption for GPU 0. Status:Success, value:0
  > Riva waiting for Triton server to load all models...retrying in 1 second
  > Triton server died before reaching ready state. Terminating Riva startup.

Thank you for your time and guideance.