Michal Guzek comments

Results 93 comments of


                                            Michal Guzek

[TRTLLM-4932] Add CLI accuracy tests for Llama-3_3-Nemotron-Super-49B-v1 and LLM API FP8 variant

/bot run

[TRTLLM-4932] Add CLI accuracy tests for Llama-3_3-Nemotron-Super-49B-v1 and LLM API FP8 variant

/bot run

[TRTLLM-4932] Add CLI accuracy tests for Llama-3.3-70B-Instruct and LLM API BF16 variant

/bot run

[TRTLLM-4932] Add CLI accuracy tests for Llama-3.3-70B-Instruct and LLM API BF16 variant

/bot kill

[TRTLLM-4932] Add CLI accuracy tests for Llama-3.3-70B-Instruct and LLM API BF16 variant

/bot run

[TRTLLM-4932] Add CLI accuracy tests for Llama-3.3-70B-Instruct and LLM API BF16 variant

/bot run

[TRTLLM-4932] Add CLI accuracy tests for Llama-3.3-70B-Instruct and LLM API BF16 variant

> [PR_Github #5409](https://nv/trt-llm-cicd/job/helpers/job/PR_Github/5409/) [ run ] completed with state `SUCCESS` [/LLM/main/L0_MergeRequest_PR pipeline #3946](https://nv/trt-llm-cicd/job/main/job/L0_MergeRequest_PR/3946/) completed with status: 'FAILURE' I don't see any failures in that test? https://prod.blsm.nvidia.com/sw-tensorrt-top-1/job/LLM/job/main/job/L0_MergeRequest_PR/3946/testReport/

[TRTLLM-4932] Add CLI accuracy tests for Llama-3.3-70B-Instruct and LLM API BF16 variant

/bot run

[TRTLLM-4932] Add CLI accuracy tests for Llama-3.3-70B-Instruct and LLM API BF16 variant

/bot run

Initialization failure of TensorRT 8.5.1.7 when running bcdu model on GPU A5000

Thanks for the updated ticket info. Could you mention your OS version just for reference? Also, have you tried running the onnx with https://github.com/NVIDIA/TensorRT/tree/main/samples/trtexec rather than ORT?