(vllm) Fixes

patches/vllm-project/vllm/v0.5.5/0001-pascal-support.patch

@@ -9,3 +9,17 @@
 
  # Supported AMD GPU architectures.
  set(HIP_SUPPORTED_ARCHS "gfx906;gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100")
+--- a/Dockerfile
++++ b/Dockerfile
+@@ -178,7 +178,10 @@ 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=bind,from=mamba-builder,src=/usr/src/mamba,target=/usr/src/mamba \
+     --mount=type=cache,target=/root/.cache/pip \

patches/vllm-project/vllm/v0.6.2/0000-sccache.patch

@@ -1,28 +1,21 @@
 --- a/Dockerfile
 +++ b/Dockerfile
-@@ -80,9 +80,9 @@ ARG nvcc_threads=8
- ENV NVCC_THREADS=$nvcc_threads
-
- ARG USE_SCCACHE
--ARG SCCACHE_BUCKET_NAME=vllm-build-sccache
--ARG SCCACHE_REGION_NAME=us-west-2
--ARG SCCACHE_S3_NO_CREDENTIALS=0
-+ARG ACTIONS_CACHE_URL
-+ARG ACTIONS_RUNTIME_TOKEN
-+ARG SCCACHE_GHA_ENABLED=0
+@@ -86,15 +86,15 @@ ARG SCCACHE_S3_NO_CREDENTIALS=0
  # if USE_SCCACHE is set, use sccache to speed up compilation
  RUN --mount=type=cache,target=/root/.cache/pip \
      --mount=type=bind,source=.git,target=.git \
-@@ -92,9 +92,9 @@ RUN --mount=type=cache,target=/root/.cache/pip \
++    --mount=type=secret,id=ACTIONS_CACHE_URL,env=ACTIONS_CACHE_URL \
++    --mount=type=secret,id=ACTIONS_RUNTIME_TOKEN,env=ACTIONS_RUNTIME_TOKEN \
+     if [ "$USE_SCCACHE" = "1" ]; then \
+         echo "Installing sccache..." \
+         && curl -L -o sccache.tar.gz https://github.com/mozilla/sccache/releases/download/v0.8.1/sccache-v0.8.1-x86_64-unknown-linux-musl.tar.gz \
          && tar -xzf sccache.tar.gz \
          && sudo mv sccache-v0.8.1-x86_64-unknown-linux-musl/sccache /usr/bin/sccache \
          && rm -rf sccache.tar.gz sccache-v0.8.1-x86_64-unknown-linux-musl \
 -        && export SCCACHE_BUCKET=${SCCACHE_BUCKET_NAME} \
 -        && export SCCACHE_REGION=${SCCACHE_REGION_NAME} \
 -        && export SCCACHE_S3_NO_CREDENTIALS=${SCCACHE_S3_NO_CREDENTIALS} \
-+        && export ACTIONS_CACHE_URL=${ACTIONS_CACHE_URL} \
-+        && export ACTIONS_RUNTIME_TOKEN=${ACTIONS_RUNTIME_TOKEN} \
-+        && export SCCACHE_GHA_ENABLED=${SCCACHE_GHA_ENABLED} \
++        && export SCCACHE_GHA_ENABLED=1 \
          && export SCCACHE_IDLE_TIMEOUT=0 \
          && export CMAKE_BUILD_TYPE=Release \
          && sccache --show-stats \