We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 6f8c7a7 commit d681bb9Copy full SHA for d681bb9
1 file changed
examples/vllm_serve/Dockerfile
@@ -28,12 +28,6 @@ RUN pip install flash-attn==2.7.4.post1 --no-build-isolation
28
# Pre-compile CUDA extensions to avoid compilation time during runtime
29
RUN python3 -c "import modelopt.torch.quantization.extensions as ext; ext.precompile()" || true
30
31
-# Install requirements from examples (excluding windows examples)
32
-RUN find Model-Optimizer/examples -name "requirements.txt" | grep -v "windows" | while read req_file; do \
33
- echo "Installing from $req_file"; \
34
- pip install -r "$req_file" || echo "Warning: Failed to install from $req_file"; \
35
- done
36
-
37
# Allow users to run without root
38
RUN chmod -R 777 /workspace
39
0 commit comments