# Unable to start riva **URL:** \ **Category:** Nemotron Speech + Riva\ **Created:** [February 11, 2022, 9:23pm UTC](https://forums.developer.nvidia.com/t/unable-to-start-riva/203236 "2022-02-11T21:23:35Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![javier7](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@javier7](https://forums.developer.nvidia.com/u/javier7)\ **Post date:** [February 11, 2022, 9:23pm UTC](https://forums.developer.nvidia.com/t/unable-to-start-riva/203236/1 "2022-02-11T21:23:35Z")
Please provide the following information when requesting support. Hardware - NVIDIA GeForce RTX 3060 Laptop GPU Hardware - 11th Gen Intel(R) Core™ i7-11800H @ 2.30GHz Operating System - Ubuntu 20.04.3 LTS Riva Version - 1.9.0-beta After following the quick start guide (both of them) and executing succesfully $ bash riva\_init.sh … Riva initialization complete. Run ./riva\_start.sh to launch services. trying to start the following command: $ 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 … ---
**Author:** ![javier7](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@javier7](https://forums.developer.nvidia.com/u/javier7)\ **Post date:** [February 11, 2022, 9:27pm UTC](https://forums.developer.nvidia.com/t/unable-to-start-riva/203236/2 "2022-02-11T21:27:22Z")
here is the output of $ docker logs riva-speech [riva-speech.log.zip](https://forums.developer.nvidia.com/uploads/short-url/m3d7BxelPVWt3wG2gOqDqi3h6BU.zip) (56.3 KB) ---
**Author:** ![javier7](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@javier7](https://forums.developer.nvidia.com/u/javier7)\ **Post date:** [February 12, 2022, 9:58pm UTC](https://forums.developer.nvidia.com/t/unable-to-start-riva/203236/3 "2022-02-12T21:58:27Z")
Same issue on a different system with ubuntu 18.04 Hardware - NVIDIA GeForce RTX 2060 SUPER Hardware - AMD Ryzen 9 3900XT 12-Core Processor Operating System - Ubuntu 18.04.6 LTS Riva Version - 1.9.0-beta [riva-speech-18.04.log.zip](https://forums.developer.nvidia.com/uploads/short-url/xEv6FiO8GJyNdFmF6U0osaAoDW3.zip) (48.8 KB) ---
**Author:** ![rvinobha](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/rvinobha/32/14047_2.png) [@rvinobha](https://forums.developer.nvidia.com/u/rvinobha)\ **Post date:** [March 2, 2022, 8:09am UTC](https://forums.developer.nvidia.com/t/unable-to-start-riva/203236/6 "2022-03-02T08:09:57Z")
Hi @javier7 , Thanks for your post and your interest in Riva, Apologies for the delay Thanks for sharing the logs for both the machines that you have tried upon, Analyzing the logs i can quickly find in both the machines `Cuda Error in copyToDevice: 2 (out of memory)` Please find the **Server Hardware** requirement link below [https://docs.nvidia.com/deeplearning/riva/user-guide/docs/support-matrix.html#server-hardware](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/support-matrix.html#server-hardware) As the link suggests, _Care must be taken to not exceed the memory available when selecting models to deploy. 16+GB VRAM is recommended._ As Both RTX 2060 and RTX 3060 Laptop GPU will have VRAM less than 16GB, I would recommend to comment out the models that will not be used in the **config.sh** file, details on where config.sh is located is available in the quick start guide > **[Quick Start Guide — NVIDIA Riva](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/quick-start-guide.html)** I am attaching a screenshot below for reference, For example i want to use the TTS model (text to speech), then i can comment out all the models that I dont need by adding # to the start of those lines (Highlighted by Yellow Box) and uncommenting the model that i need to use (Here in below image highlighted by green box) and vice versa You can do the same as per your requirement/usecase in the **config.sh** file, ![image](https://global.discourse-cdn.com/nvidia/original/3X/6/1/6129966ce005938bd60cc39f574a3e9b05cb9802.png) Alternatively we can also disable service as a whole if not needed in config.sh, lines below # Enable or Disable Riva Services ```auto service_enabled_asr=true service_enabled_nlp=true service_enabled_tts=true ``` set to true or false depending upon your requirement/usecase, So the Overall flow, here I would **recommend you to try** 1. Navigate inside the quickstart directory `cd riva_quickstart_v1.9.0-beta` 2. Run `bash riva_clean.sh` 3. Modify the **config.sh** file to select only the model/service for your usecase/requirement as instructed above 4. Run `bash riva_init.sh` (If possbile please share the console output ; Command `command | tee ~/outputfile.txt` in our case `bash riva_init.sh | tee riva_init_log.txt`, Please share the riva\_init\_logs.txt) 5. Run `bash riva_start.sh` Please try the above steps and let me know whether it works, also please do share the Nvidia Driver Version used, command `nvidia-smi` ---
**Author:** ![javier7](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@javier7](https://forums.developer.nvidia.com/u/javier7)\ **Post date:** [March 2, 2022, 7:39pm UTC](https://forums.developer.nvidia.com/t/unable-to-start-riva/203236/7 "2022-03-02T19:39:06Z")
Amazing, I understand, thanks for the answer, is it possible to run the components that do not fit the memory on one gpu on the other gpu that is in the other system in the same lan?? ---
**Author:** ![rvinobha](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/rvinobha/32/14047_2.png) [@rvinobha](https://forums.developer.nvidia.com/u/rvinobha)\ **Post date:** [March 10, 2022, 7:15pm UTC](https://forums.developer.nvidia.com/t/unable-to-start-riva/203236/8 "2022-03-10T19:15:23Z")
Hi @javier7 , Thanks you for your interest in Riva, Unfortunately, Currently at the moment, we do not have support for running/inferencing over Multiple Machines with GPU over the same LAN Network, You have to run two Riva Instances over the two machines separately ---
**Author:** ![javier7](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@javier7](https://forums.developer.nvidia.com/u/javier7)\ **Post date:** [March 12, 2022, 12:26am UTC](https://forums.developer.nvidia.com/t/unable-to-start-riva/203236/9 "2022-03-12T00:26:43Z")
I understand, Thank you very much