liu21yd

ValueError: bytes is too large when running scripts/run_train_text.sh

1

**Detail message:** Traceback (most recent call last): File "/user_work_path/miniconda3/envs/lwm/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/user_work_path/miniconda3/envs/lwm/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/user_work_path/train/codes/LWM/lwm/train.py", line 396, in...

Encountered an error: peer access is not supported between these two devices in tensorrt_llm::runtime::IpcMemory::allocateIpcMemory()

1

**I built TensoRT-LLM 0.9.0 from source code base on nvcr.io/nvidia/tritonserver:24.02-py3 , and run scripts or commands from https://github.com/NVIDIA/TensorRT-LLM/blob/main/docker/Dockerfile.multi.** **I convert the checkpoint and built engine successfully by following command:** ```...

Result is out of order when using http stream mode

4

1. I built the image from source , using the TensorRT-LLM and tensorrtllm_backend main brand at September 25th。 2. I built qwen2.5 14B and start the triton server successfully. I...