(vllm) Fix patch for main

sasha0552 · Nov 27, 2024 · 48f64cd · 48f64cd
1 parent bb88000
commit 48f64cd
Show file tree

Hide file tree

Showing 3 changed files with 26 additions and 1 deletion.
diff --git a/patches/vllm-project/vllm/main b/patches/vllm-project/vllm/main
diff --git a/patches/vllm-project/vllm/main/0000-environment-variables.patch b/patches/vllm-project/vllm/main/0000-environment-variables.patch
@@ -0,0 +1 @@
+../v0.6.2/0000-environment-variables.patch
diff --git a/patches/vllm-project/vllm/main/0001-pascal-support.patch b/patches/vllm-project/vllm/main/0001-pascal-support.patch
@@ -0,0 +1,25 @@
+--- a/CMakeLists.txt
++++ b/CMakeLists.txt
+@@ -34,7 +34,7 @@ install(CODE "set(CMAKE_INSTALL_LOCAL_ONLY TRUE)" ALL_COMPONENTS)
+ set(PYTHON_SUPPORTED_VERSIONS "3.9" "3.10" "3.11" "3.12")
+
+ # Supported NVIDIA architectures.
+-set(CUDA_SUPPORTED_ARCHS "7.0;7.2;7.5;8.0;8.6;8.7;8.9;9.0")
++set(CUDA_SUPPORTED_ARCHS "6.0;6.1;7.0;7.2;7.5;8.0;8.6;8.7;8.9;9.0")
+
+ # Supported AMD GPU architectures.
+ set(HIP_SUPPORTED_ARCHS "gfx906;gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101")
+--- a/Dockerfile
++++ b/Dockerfile
+@@ -171,7 +171,10 @@ RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/
+ # install vllm wheel first, so that torch etc will be installed
+ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist \
+     --mount=type=cache,target=/root/.cache/pip \
+-    python3 -m pip install dist/*.whl --verbose
++    python3 -m pip install dist/*.whl --verbose && \
++    export PIP_EXTRA_INDEX_URL="https://sasha0552.github.io/pascal-pkgs-ci/" && \
++    python3 -m pip install transient-package && \
++    transient-package install --source triton --target triton-pascal
+
+ RUN --mount=type=cache,target=/root/.cache/pip \
+     . /etc/environment && \