Kaiyu Xie
Kaiyu Xie
/bot reuse-pipeline
@RuibaiXu @nv-guomingz Please note that, the latest `docs/source/performance/perf-overview.md` is not using `trtllm-build` command anymore. ([link](https://github.com/NVIDIA/TensorRT-LLM/blob/main/docs/source/performance/perf-overview.md?plain=1)) > the right doc after change shouled be --max_input_len 2048 --max_seq_len 4096 @RuibaiXu Just FYI...
/bot reuse-pipeline
/bot run --stage-list "Build-Docker-Images"
I see that this is going to be addressed by https://github.com/NVIDIA/TensorRT-LLM/pull/3003. @Pradeep-18062002 Thanks a lot for reporting the issue and help fix it!
> HI [@xunuohope1107](https://github.com/xunuohope1107) , Please add `processor = AutoProcessor.from_pretrained(self.args.hf_model_dir)` in `tensorrt_llm/runtime/multimodal_model_runner.py`. > > Thanks. Hi @sunnyqgg , I see that the issue is still being reported by the users, can...
The `trtllm-bench` part looks good to me. @suyoggupta Is it possible to split the PR so that it only includes the changes of "enables the integration of TRTLLM-bench with AutoDeploy"?...
> > The `trtllm-bench` part looks good to me. > > @suyoggupta Is it possible to split the PR so that it only includes the changes of "enables the integration...