TensorRT

Topic	Replies	Views	Activity
TensorRT 8.2 and Framework Integrations are out now! tensorrt The latest release of TensorRT, 8.2 GA, and TensorRT Integrations for PyTorch and TensorFlow, is now available for download. Highlight includes: TensorRT 8.2 Optimizations for T5 and GPT-2 deliver real time translati…	4	6328	January 10, 2025
Best practices for reporting an issue or bug relating to TensorRT	0	9064	September 21, 2018
TensorRT 10.6: fused FP16 xmma GEMM kernel hangs under CUDA Graph replay – CTAs spin forever on a semaphore counter that reads 0 after their own RED.A cudnn	0	13	November 5, 2026
Sasha: a local Rust voice assistant running on an RTX 5080 + Quadro RTX 4000 + AMD 6800XT llama	0	68	October 29, 2026
Best preprocessing for presentation datasets on NVIDIA GPUs	4	124	October 9, 2026
PyTorch Conditionals that run on GPU / TensorRT tensorrt , cuda , pytorch	4	192	October 4, 2026
Request for NIM API Rate Limit Increase: 40 RPM to 200 RPM (Key ID ends with 933902ee) api , access-control , nim , agentic-ai	0	41	September 26, 2026
BF16 strongly-typed engine build segfaults in Myelin on RTX 5090 (sm_120) — identical network builds fine as FP16; reproduced on TensorRT 11.0 / 11.1 cudnn	3	142	August 31, 2026
Aliased I/O TensorRT plugin bug cudnn	1	88	August 28, 2026
TensorRT 10.14 silently produces wrong detection scores for D-FINE (DETR-style) models on RTX 5090 / sm_120 — default build drops 12 detections to 0, cudnn , onnx , deepstream	2	170	August 28, 2026
TensorRT inferior scalability on A10, L4 possibly due to locking issues	8	444	August 17, 2026
No artifact → no claim → exit 1. No hash → no trust. No zip → no history. System records existence, not truth	0	75	August 13, 2026
AOT tensorrt.plugin reloads plugin PTX via cuModuleLoadData on every enqueue in dynamic-shape engines cudnn	2	163	August 6, 2026
Techniques to Imporve TensorRT Model Inference Speed tensorrt , cudnn	3	493	August 5, 2026
100m Person Detection & Tracking at 35+ FPS on Jetson Orin Nano (8GB) jetson	3	756	August 5, 2026
TensorRT Engine Creation Fails with “tensor volume exceeds 2147483648” on MobileNet SSD v2 in DeepStream 7.1 (Jetson Orin Nano) cudnn , jetson , deepstream	2	160	August 4, 2026
FinC2E — Governance-First AI for AML/KYC & Audit-Ready Decision Support (Human-in-the-Loop) architecture-and-design , system-management-and-architecture , aerial-research-cloud	3	228	August 4, 2026
Compute bottleneck evaluating multiple trajectories through a 7B VLM (VLA Architecture Design) tensorrt , cuda , nemo , llm	4	236	August 4, 2026
If NVINT8 exists, the performance is …	5	505	July 31, 2026
INT8 Tensor Core corruption on Turing sm_75 cuBLAS llama.cpp BPE tokenizer tensorrt , cuda , cudnn , cublas , llama	3	451	July 31, 2026
[Test] Hey There, Need some Help	7	174	July 7, 2026
TensorRT Q/DQ: how to keep Gather in INT8	1	83	June 30, 2026
Dynamic shapes not dynamic at all tensorrt , cudnn	1	263	June 30, 2026
On Board Gpu cudnn	2	87	June 19, 2026
Latency Gains using TensorRT	1	181	June 19, 2026
2:4 sparsity doesnot improve inference performance on RTX 3090 tensorrt	15	3926	June 4, 2026
Request for NVIDIA NIM API Rate Limit Increase (40 → 200 RPM) nim , agentic-ai , deepseek	3	519	June 4, 2026
Tensorflow Container for use on H200? cudnn	4	375	June 2, 2026
Problem with accessing resources: TensorRT libraries not found. Check that current user has access to GPU camera	1	139	May 30, 2026
TensorRT Custom Plugin Produces Non-Deterministic Results with Identical Inputs Across 20 Iterations cuda , kernel , cudnn	1	128	May 30, 2026

TensorRT 8.2 and Framework Integrations are out now!

tensorrt

The latest release of TensorRT, 8.2 GA, and TensorRT Integrations for PyTorch and TensorFlow, is now available for download. Highlight includes: TensorRT 8.2 Optimizations for T5 and GPT-2 deliver real time translati…