Hugging Face's logo

Spaces:
yusufs
/
llama32-3b-instruct
Paused

App Files Community
yusufs commited on
Commit
ae21665
·
verified ·
1 Parent(s): 852d95b

Update Dockerfile

Browse files
Files changed (1) hide show
  1. Dockerfile +1 -0
Dockerfile CHANGED
@@ -62,6 +62,7 @@ RUN pip install uv setuptools
62
  # Install vLLM
63
  # RUN uv pip install --system vllm==0.10.0 torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu113
64
  # Downgrade triton because following error occured when using triton==3.3.1
 
65
  # /usr/local/lib/python3.12/dist-packages/vllm/attention/ops/prefix_prefill.py:36:0: error: Failures have been detected while processing an MLIR pass pipeline
66
  # /usr/local/lib/python3.12/dist-packages/vllm/attention/ops/prefix_prefill.py:36:0: note: Pipeline failed while executing [`ConvertTritonGPUToLLVM` on 'builtin.module' operation]: reproducer generated at `std::errs, please share the reproducer above with Triton project.`
67
  # INFO: 10.16.9.222:28100 - "POST /v1/chat/completions HTTP/1.1" 500 Internal Server Error
 
62
  # Install vLLM
63
  # RUN uv pip install --system vllm==0.10.0 torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu113
64
  # Downgrade triton because following error occured when using triton==3.3.1
65
+ # https://github.com/vllm-project/vllm/issues/20259#issuecomment-3157159183
66
  # /usr/local/lib/python3.12/dist-packages/vllm/attention/ops/prefix_prefill.py:36:0: error: Failures have been detected while processing an MLIR pass pipeline
67
  # /usr/local/lib/python3.12/dist-packages/vllm/attention/ops/prefix_prefill.py:36:0: note: Pipeline failed while executing [`ConvertTritonGPUToLLVM` on 'builtin.module' operation]: reproducer generated at `std::errs, please share the reproducer above with Triton project.`
68
  # INFO: 10.16.9.222:28100 - "POST /v1/chat/completions HTTP/1.1" 500 Internal Server Error