Fix Dockerfile not installing correct version of DeepEP for arm build (sgl-project#11773)

Author: kyleliang-nv

.github/workflows/release-docker-dev.yml

@@ -15,11 +15,13 @@ jobs:
           - runner: x64-docker-build-node
             platform: linux/amd64
             build_type: all
+            grace_blackwell: 0
             tag: dev-x86
             version: 12.9.1
           - runner: arm-docker-build-node
             platform: linux/arm64
             build_type: all
+            grace_blackwell: 1
             tag: dev-arm64
             version: 12.9.1
     steps:
@@ -51,7 +53,7 @@ jobs:
 
       - name: Build and Push Dev Image
         run: |
-          docker buildx build --platform ${{ matrix.platform }} --push -f docker/Dockerfile --build-arg CUDA_VERSION=${{ matrix.version }} --build-arg BUILD_TYPE=${{ matrix.build_type }} --build-arg CMAKE_BUILD_PARALLEL_LEVEL=$(nproc) -t lmsysorg/sglang:${{ matrix.tag }} --no-cache .
+          docker buildx build --platform ${{ matrix.platform }} --push -f docker/Dockerfile --build-arg CUDA_VERSION=${{ matrix.version }} --build-arg BUILD_TYPE=${{ matrix.build_type }} --build-arg GRACE_BLACKWELL=${{ matrix.grace_blackwell }} --build-arg CMAKE_BUILD_PARALLEL_LEVEL=$(nproc) -t lmsysorg/sglang:${{ matrix.tag }} --no-cache .
 
   create-manifests:
     runs-on: ubuntu-22.04

.github/workflows/release-docker.yml

@@ -16,6 +16,7 @@ jobs:
         variant:
           - cuda_version: "12.9.1"
             build_type: "all"
+            grace_blackwell: 0
     runs-on: x64-docker-build-node
     steps:
       - name: Delete huge unnecessary tools folder
@@ -55,6 +56,7 @@ jobs:
             -f docker/Dockerfile \
             --build-arg CUDA_VERSION=${{ matrix.variant.cuda_version }} \
             --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
+            --build-arg GRACE_BLACKWELL=${{ matrix.variant.grace_blackwell }} \
             -t lmsysorg/sglang:${tag} \
             --no-cache \
             .
@@ -67,6 +69,7 @@ jobs:
         variant:
           - cuda_version: "12.9.1"
             build_type: "all"
+            grace_blackwell: 1
     runs-on: arm-docker-build-node
     steps:
       - name: Delete huge unnecessary tools folder
@@ -95,6 +98,7 @@ jobs:
             -f docker/Dockerfile \
             --build-arg CUDA_VERSION=${{ matrix.variant.cuda_version }} \
             --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
+            --build-arg GRACE_BLACKWELL=${{ matrix.variant.grace_blackwell }} \
             -t lmsysorg/sglang:${tag} \
             --no-cache \
             .

docker/Dockerfile

@@ -2,6 +2,7 @@ ARG CUDA_VERSION=12.9.1
 FROM nvidia/cuda:${CUDA_VERSION}-cudnn-devel-ubuntu22.04 AS base
 ARG TARGETARCH
 
+ARG GRACE_BLACKWELL=0
 ARG BUILD_TYPE=all
 ARG BRANCH_TYPE=remote
 ARG DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee
@@ -99,7 +100,7 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip setuptools wheel html5li
 # Download NVSHMEM source files
 # We use Tom's DeepEP fork for GB200 for now
 RUN wget https://developer.download.nvidia.com/compute/redist/nvshmem/3.3.9/source/nvshmem_src_cuda12-all-all-3.3.9.tar.gz && \
-    if [ "$BUILD_TYPE" = "blackwell_aarch64" ]; then \
+    if [ "$GRACE_BLACKWELL" = "1" ]; then \
       git clone https://github.com/fzyzcjy/DeepEP.git \
       && cd DeepEP && git checkout 1b14ad661c7640137fcfe93cccb2694ede1220b0 && sed -i 's/#define NUM_CPU_TIMEOUT_SECS 100/#define NUM_CPU_TIMEOUT_SECS 1000/' csrc/kernels/configs.cuh && cd .. ; \
     else \
@@ -112,7 +113,7 @@ RUN wget https://developer.download.nvidia.com/compute/redist/nvshmem/3.3.9/sour
 
 # Build and install NVSHMEM
 RUN cd /sgl-workspace/nvshmem && \
-    if [ "$BUILD_TYPE" = "blackwell" ] || [ "$BUILD_TYPE" = "blackwell_aarch" ]; then CUDA_ARCH="90;100;120"; else CUDA_ARCH="90"; fi && \
+    if [ "$GRACE_BLACKWELL" = "1" ]; then CUDA_ARCH="90;100;120"; else CUDA_ARCH="90"; fi && \
     NVSHMEM_SHMEM_SUPPORT=0 \
     NVSHMEM_UCX_SUPPORT=0 \
     NVSHMEM_USE_NCCL=0 \