Split workflow for releasing runtime docker (#21563)
This commit is contained in:
Baizhou Zhang
@@ -1,15 +1,9 @@
|
||||
name: Release Docker Images
|
||||
#
|
||||
# This workflow builds and publishes both framework and runtime Docker images:
|
||||
#
|
||||
# Framework images (full development environment):
|
||||
# This workflow builds and publishes framework Docker images (full development environment):
|
||||
# - lmsysorg/sglang:v{version}, lmsysorg/sglang:latest
|
||||
# - lmsysorg/sglang:v{version}-cu130, lmsysorg/sglang:latest-cu130
|
||||
#
|
||||
# Runtime images (production-optimized, ~50% smaller):
|
||||
# - lmsysorg/sglang:v{version}-runtime, lmsysorg/sglang:latest-runtime
|
||||
# - lmsysorg/sglang:v{version}-cu130-runtime, lmsysorg/sglang:latest-cu130-runtime
|
||||
#
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
@@ -102,28 +96,6 @@ jobs:
|
||||
echo "Pushed digest: ${DIGEST}"
|
||||
echo "${DIGEST}" > /tmp/digest-cu129-amd64-framework.txt
|
||||
|
||||
- name: Build and Push AMD64 Runtime
|
||||
run: |
|
||||
version=${{ steps.version.outputs.version }}
|
||||
|
||||
docker buildx build \
|
||||
--target runtime \
|
||||
--platform linux/amd64 \
|
||||
--output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
|
||||
-f docker/Dockerfile \
|
||||
--build-arg CUDA_VERSION=${{ matrix.variant.cuda_version }} \
|
||||
--build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
|
||||
--build-arg GRACE_BLACKWELL=${{ matrix.variant.grace_blackwell }} \
|
||||
--build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
|
||||
--build-arg SGL_VERSION=${version} \
|
||||
--metadata-file /tmp/metadata-cu129-runtime.json \
|
||||
--no-cache \
|
||||
.
|
||||
|
||||
DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu129-runtime.json'))['containerimage.digest'])")
|
||||
echo "Pushed digest: ${DIGEST}"
|
||||
echo "${DIGEST}" > /tmp/digest-cu129-amd64-runtime.txt
|
||||
|
||||
- name: Build and Push AMD64 Framework (CUDA 13)
|
||||
run: |
|
||||
version=${{ steps.version.outputs.version }}
|
||||
@@ -146,28 +118,6 @@ jobs:
|
||||
echo "Pushed digest: ${DIGEST}"
|
||||
echo "${DIGEST}" > /tmp/digest-cu130-amd64-framework.txt
|
||||
|
||||
- name: Build and Push AMD64 Runtime (CUDA 13)
|
||||
run: |
|
||||
version=${{ steps.version.outputs.version }}
|
||||
|
||||
docker buildx build \
|
||||
--target runtime \
|
||||
--platform linux/amd64 \
|
||||
--output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
|
||||
-f docker/Dockerfile \
|
||||
--build-arg CUDA_VERSION=13.0.1 \
|
||||
--build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
|
||||
--build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
|
||||
--build-arg GRACE_BLACKWELL=0 \
|
||||
--build-arg SGL_VERSION=${version} \
|
||||
--metadata-file /tmp/metadata-cu130-runtime.json \
|
||||
--no-cache \
|
||||
.
|
||||
|
||||
DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu130-runtime.json'))['containerimage.digest'])")
|
||||
echo "Pushed digest: ${DIGEST}"
|
||||
echo "${DIGEST}" > /tmp/digest-cu130-amd64-runtime.txt
|
||||
|
||||
- name: Upload digests
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
@@ -245,28 +195,6 @@ jobs:
|
||||
echo "Pushed digest: ${DIGEST}"
|
||||
echo "${DIGEST}" > /tmp/digest-cu129-arm64-framework.txt
|
||||
|
||||
- name: Build and Push ARM64 Runtime
|
||||
run: |
|
||||
version=${{ steps.version.outputs.version }}
|
||||
|
||||
docker buildx build \
|
||||
--target runtime \
|
||||
--platform linux/arm64 \
|
||||
--output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
|
||||
-f docker/Dockerfile \
|
||||
--build-arg CUDA_VERSION=${{ matrix.variant.cuda_version }} \
|
||||
--build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
|
||||
--build-arg GRACE_BLACKWELL=${{ matrix.variant.grace_blackwell }} \
|
||||
--build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
|
||||
--build-arg SGL_VERSION=${version} \
|
||||
--metadata-file /tmp/metadata-cu129-runtime.json \
|
||||
--no-cache \
|
||||
.
|
||||
|
||||
DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu129-runtime.json'))['containerimage.digest'])")
|
||||
echo "Pushed digest: ${DIGEST}"
|
||||
echo "${DIGEST}" > /tmp/digest-cu129-arm64-runtime.txt
|
||||
|
||||
- name: Build and Push ARM64 Framework (CUDA 13)
|
||||
run: |
|
||||
version=${{ steps.version.outputs.version }}
|
||||
@@ -289,27 +217,6 @@ jobs:
|
||||
echo "Pushed digest: ${DIGEST}"
|
||||
echo "${DIGEST}" > /tmp/digest-cu130-arm64-framework.txt
|
||||
|
||||
- name: Build and Push ARM64 Runtime (CUDA 13)
|
||||
run: |
|
||||
version=${{ steps.version.outputs.version }}
|
||||
|
||||
docker buildx build \
|
||||
--target runtime \
|
||||
--platform linux/arm64 \
|
||||
--output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
|
||||
-f docker/Dockerfile \
|
||||
--build-arg CUDA_VERSION=13.0.1 \
|
||||
--build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
|
||||
--build-arg GRACE_BLACKWELL=1 \
|
||||
--build-arg SGL_VERSION=${version} \
|
||||
--metadata-file /tmp/metadata-cu130-runtime.json \
|
||||
--no-cache \
|
||||
.
|
||||
|
||||
DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu130-runtime.json'))['containerimage.digest'])")
|
||||
echo "Pushed digest: ${DIGEST}"
|
||||
echo "${DIGEST}" > /tmp/digest-cu130-arm64-runtime.txt
|
||||
|
||||
- name: Upload digests
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
@@ -373,15 +280,10 @@ jobs:
|
||||
run: |
|
||||
version=${{ steps.version.outputs.version }}
|
||||
|
||||
# Load all digests
|
||||
CU129_AMD64_FW=$(cat /tmp/digests/amd64/digest-cu129-amd64-framework.txt)
|
||||
CU129_AMD64_RT=$(cat /tmp/digests/amd64/digest-cu129-amd64-runtime.txt)
|
||||
CU130_AMD64_FW=$(cat /tmp/digests/amd64/digest-cu130-amd64-framework.txt)
|
||||
CU130_AMD64_RT=$(cat /tmp/digests/amd64/digest-cu130-amd64-runtime.txt)
|
||||
CU129_ARM64_FW=$(cat /tmp/digests/arm64/digest-cu129-arm64-framework.txt)
|
||||
CU129_ARM64_RT=$(cat /tmp/digests/arm64/digest-cu129-arm64-runtime.txt)
|
||||
CU130_ARM64_FW=$(cat /tmp/digests/arm64/digest-cu130-arm64-framework.txt)
|
||||
CU130_ARM64_RT=$(cat /tmp/digests/arm64/digest-cu130-arm64-runtime.txt)
|
||||
|
||||
# Create versioned framework manifest (default)
|
||||
docker buildx imagetools create \
|
||||
@@ -395,18 +297,6 @@ jobs:
|
||||
lmsysorg/sglang@${CU129_AMD64_FW} \
|
||||
lmsysorg/sglang@${CU129_ARM64_FW}
|
||||
|
||||
# Create versioned runtime manifest
|
||||
docker buildx imagetools create \
|
||||
-t lmsysorg/sglang:v${version}-runtime \
|
||||
lmsysorg/sglang@${CU129_AMD64_RT} \
|
||||
lmsysorg/sglang@${CU129_ARM64_RT}
|
||||
|
||||
# Create latest runtime manifest
|
||||
docker buildx imagetools create \
|
||||
-t lmsysorg/sglang:latest-runtime \
|
||||
lmsysorg/sglang@${CU129_AMD64_RT} \
|
||||
lmsysorg/sglang@${CU129_ARM64_RT}
|
||||
|
||||
# Create versioned CUDA 13 framework manifest
|
||||
docker buildx imagetools create \
|
||||
-t lmsysorg/sglang:v${version}-cu130 \
|
||||
@@ -418,15 +308,3 @@ jobs:
|
||||
-t lmsysorg/sglang:latest-cu130 \
|
||||
lmsysorg/sglang@${CU130_AMD64_FW} \
|
||||
lmsysorg/sglang@${CU130_ARM64_FW}
|
||||
|
||||
# Create versioned CUDA 13 runtime manifest
|
||||
docker buildx imagetools create \
|
||||
-t lmsysorg/sglang:v${version}-cu130-runtime \
|
||||
lmsysorg/sglang@${CU130_AMD64_RT} \
|
||||
lmsysorg/sglang@${CU130_ARM64_RT}
|
||||
|
||||
# Create latest CUDA 13 runtime manifest
|
||||
docker buildx imagetools create \
|
||||
-t lmsysorg/sglang:latest-cu130-runtime \
|
||||
lmsysorg/sglang@${CU130_AMD64_RT} \
|
||||
lmsysorg/sglang@${CU130_ARM64_RT}
|
||||
|
||||
Reference in New Issue
Block a user