From 05abb5e8c30940f80a9c33d29a940481f2403d2a Mon Sep 17 00:00:00 2001
From: sasha0552 <admin@sasha0552.org>
Date: Tue, 8 Oct 2024 15:30:53 +0000
Subject: [PATCH] (vllm) Pass secrets as secrets

---
 .github/actions/build-vllm/action.yml         | 14 +++++++------
 .../vllm/v0.5.5/0000-sccache.patch            | 20 +++++++------------
 .../0002-docker-install-patched-triton.patch  |  2 +-
 3 files changed, 16 insertions(+), 20 deletions(-)

diff --git a/.github/actions/build-vllm/action.yml b/.github/actions/build-vllm/action.yml
index 344d571..8e9ac99 100644
--- a/.github/actions/build-vllm/action.yml
+++ b/.github/actions/build-vllm/action.yml
@@ -85,14 +85,15 @@ runs:
         target: build
 
         build-args: |
-          ACTIONS_CACHE_URL=${{ env.ACTIONS_CACHE_URL }}
-          ACTIONS_RUNTIME_TOKEN=${{ env.ACTIONS_RUNTIME_TOKEN }}
-          SCCACHE_GHA_ENABLED=1
           USE_SCCACHE=1
           torch_cuda_arch_list=6.0 6.1 7.0 7.5 8.0 8.6 8.9 9.0+PTX
           max_jobs=2
           nvcc_threads=2
 
+        secrets: |
+          ACTIONS_CACHE_URL=${{ env.ACTIONS_CACHE_URL }}
+          ACTIONS_RUNTIME_TOKEN=${{ env.ACTIONS_RUNTIME_TOKEN }}
+
     - name: Copy wheel files
       shell: bash
       run: tar --extract --file=build.tar --strip-components=1 workspace/dist && rm build.tar
@@ -125,10 +126,11 @@ runs:
         target: vllm-openai
 
         build-args: |
-          ACTIONS_CACHE_URL=${{ env.ACTIONS_CACHE_URL }}
-          ACTIONS_RUNTIME_TOKEN=${{ env.ACTIONS_RUNTIME_TOKEN }}
-          SCCACHE_GHA_ENABLED=1
           USE_SCCACHE=1
           torch_cuda_arch_list=6.0 6.1 7.0 7.5 8.0 8.6 8.9 9.0+PTX
           max_jobs=2
           nvcc_threads=2
+
+        secrets: |
+          ACTIONS_CACHE_URL=${{ env.ACTIONS_CACHE_URL }}
+          ACTIONS_RUNTIME_TOKEN=${{ env.ACTIONS_RUNTIME_TOKEN }}
diff --git a/patches/vllm-project/vllm/v0.5.5/0000-sccache.patch b/patches/vllm-project/vllm/v0.5.5/0000-sccache.patch
index 5a136a8..20ae1c1 100644
--- a/patches/vllm-project/vllm/v0.5.5/0000-sccache.patch
+++ b/patches/vllm-project/vllm/v0.5.5/0000-sccache.patch
@@ -1,26 +1,20 @@
 --- a/Dockerfile
 +++ b/Dockerfile
-@@ -85,8 +85,9 @@ ARG buildkite_commit
- ENV BUILDKITE_COMMIT=${buildkite_commit}
- 
- ARG USE_SCCACHE
--ARG SCCACHE_BUCKET_NAME=vllm-build-sccache
--ARG SCCACHE_REGION_NAME=us-west-2
-+ARG ACTIONS_CACHE_URL
-+ARG ACTIONS_RUNTIME_TOKEN
-+ARG SCCACHE_GHA_ENABLED=0
+@@ -89,14 +89,15 @@ ARG SCCACHE_BUCKET_NAME=vllm-build-sccache
+ ARG SCCACHE_REGION_NAME=us-west-2
  # if USE_SCCACHE is set, use sccache to speed up compilation
  RUN --mount=type=cache,target=/root/.cache/pip \
++    --mount=type=secret,id=ACTIONS_CACHE_URL,env=ACTIONS_CACHE_URL \
++    --mount=type=secret,id=ACTIONS_RUNTIME_TOKEN,env=ACTIONS_RUNTIME_TOKEN \
      if [ "$USE_SCCACHE" = "1" ]; then \
-@@ -95,8 +96,9 @@ RUN --mount=type=cache,target=/root/.cache/pip \
+         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 ACTIONS_CACHE_URL=${ACTIONS_CACHE_URL} \
-+        && export ACTIONS_RUNTIME_TOKEN=${ACTIONS_RUNTIME_TOKEN} \
-+        && export SCCACHE_GHA_ENABLED=${SCCACHE_GHA_ENABLED} \
++        && export SCCACHE_GHA_ENABLED=1 \
          && export SCCACHE_IDLE_TIMEOUT=0 \
          && export CMAKE_BUILD_TYPE=Release \
          && sccache --show-stats \
diff --git a/patches/vllm-project/vllm/v0.5.5/0002-docker-install-patched-triton.patch b/patches/vllm-project/vllm/v0.5.5/0002-docker-install-patched-triton.patch
index 9a1a545..f869c57 100644
--- a/patches/vllm-project/vllm/v0.5.5/0002-docker-install-patched-triton.patch
+++ b/patches/vllm-project/vllm/v0.5.5/0002-docker-install-patched-triton.patch
@@ -1,6 +1,6 @@
 --- a/Dockerfile
 +++ b/Dockerfile
-@@ -179,7 +179,10 @@ RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/
+@@ -178,7 +178,10 @@ RUN ldconfig /usr/local/cuda-$(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 \