mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-04-22 16:01:50 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat(backends): add sglang

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2026-04-14 22:38:52 +00:00
parent ad3c8c4832
commit d47e2aa93f
21 changed files with 896 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
.github/workflows/backend.yml vendored
View File

@@ -66,6 +66,19 @@ jobs:
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-sglang'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'true'
backend: "sglang"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
@@ -411,6 +424,19 @@ jobs:
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-sglang'
runs-on: 'arc-runner-set'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "sglang"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
@@ -1427,6 +1453,19 @@ jobs:
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-sglang'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:7.2.1"
skip-drivers: 'false'
backend: "sglang"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
@@ -1689,6 +1728,19 @@ jobs:
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-sglang'
runs-on: 'arc-runner-set'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "sglang"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""

27
.github/workflows/test-extra.yml vendored
View File

@@ -33,6 +33,7 @@ jobs:
ik-llama-cpp: ${{ steps.detect.outputs.ik-llama-cpp }}
turboquant: ${{ steps.detect.outputs.turboquant }}
vllm: ${{ steps.detect.outputs.vllm }}
sglang: ${{ steps.detect.outputs.sglang }}
acestep-cpp: ${{ steps.detect.outputs.acestep-cpp }}
qwen3-tts-cpp: ${{ steps.detect.outputs.qwen3-tts-cpp }}
voxtral: ${{ steps.detect.outputs.voxtral }}
@@ -589,6 +590,32 @@ jobs:
# - name: Build vllm (cpu) backend image and run gRPC e2e tests
# run: |
# make test-extra-backend-vllm
tests-sglang-grpc:
needs: detect-changes
if: needs.detect-changes.outputs.sglang == 'true' || needs.detect-changes.outputs.run-all == 'true'
runs-on: ubuntu-latest
timeout-minutes: 90
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y --no-install-recommends \
make build-essential curl unzip ca-certificates git tar
- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: '1.25.4'
- name: Free disk space
run: |
sudo rm -rf /usr/share/dotnet /opt/ghc /usr/local/lib/android /opt/hostedtoolcache/CodeQL || true
df -h
- name: Build sglang (cpu) backend image and run gRPC e2e tests
run: |
make test-extra-backend-sglang
tests-acestep-cpp:
needs: detect-changes
if: needs.detect-changes.outputs.acestep-cpp == 'true' || needs.detect-changes.outputs.run-all == 'true'