Merge branch 'main' into move-init

Author: hebiao064

.github/CI_PERMISSIONS.json

@@ -207,7 +207,7 @@
         "can_tag_run_ci_label": true,
         "can_rerun_failed_ci": true,
         "cooldown_interval_minutes": 0,
-        "reason": "top contributor"
+        "reason": "custom override"
     },
     "ZhengdQin": {
         "can_tag_run_ci_label": true,
@@ -230,7 +230,7 @@
     "airMeng": {
         "can_tag_run_ci_label": true,
         "can_rerun_failed_ci": true,
-        "cooldown_interval_minutes": 60,
+        "cooldown_interval_minutes": 0,
         "reason": "custom override"
     },
     "alisonshao": {

.github/CODEOWNERS

@@ -3,7 +3,9 @@
 /docker/npu.Dockerfile @ping1jing2 @iforgetmyname
 /python/pyproject.toml @merrymercy @Fridge003 @ispobock
 /python/sglang/multimodal_gen @mickqian
+/python/sglang/srt/batch_invariant_ops @Fridge003 @hebiao064
 /python/sglang/srt/constrained @hnyls2002 @DarkSharpness
+/python/sglang/srt/compilation @hebiao064
 /python/sglang/srt/disaggregation @ByronHsu @hnyls2002 @ShangmingCai
 /python/sglang/srt/disaggregation/ascend @ping1jing2 @iforgetmyname
 /python/sglang/srt/distributed @yizhang2077 @merrymercy @ch-wan
@@ -12,7 +14,7 @@
 /python/sglang/srt/eplb @fzyzcjy @ch-wan
 /python/sglang/srt/function_call @CatherineSue @JustinTong0323
 /python/sglang/srt/grpc @CatherineSue @slin1237
-/python/sglang/srt/layers @merrymercy @Ying1123 @Fridge003 @ispobock @HaiShaw @ch-wan @BBuf @kushanam @Edwardf0t1
+/python/sglang/srt/layers @merrymercy @Ying1123 @Fridge003 @ispobock @HaiShaw @ch-wan @BBuf @Edwardf0t1
 /python/sglang/srt/layers/quantization @ch-wan @BBuf @Edwardf0t1 @FlamingoPg @AniZpZ
 /python/sglang/srt/layers/attention/ascend_backend.py @ping1jing2 @iforgetmyname
 /python/sglang/srt/lora @Ying1123 @Fridge003 @lifuhuang
@@ -21,6 +23,7 @@
 /python/sglang/srt/mem_cache/allocator_ascend.py @ping1jing2 @iforgetmyname
 /python/sglang/srt/model_executor @merrymercy @Ying1123 @hnyls2002 @Fridge003 @ispobock
 /python/sglang/srt/model_executor/npu_graph_runner.py @ping1jing2 @iforgetmyname
+/python/sglang/srt/model_executor/piecewise_cuda_graph_runner.py @hebiao064
 /python/sglang/srt/multimodal @mickqian @JustinTong0323 @yhyang201
 /python/sglang/srt/speculative @Ying1123 @merrymercy @hnyls2002
 /sgl-kernel @zhyncs @ispobock @BBuf @yizhang2077 @merrymercy @FlamingoPg @HaiShaw

.github/workflows/nightly-test-nvidia.yml

@@ -8,14 +8,40 @@ on:
       - main
     paths:
       - "python/sglang/version.py"
+      - "test/run_suite.py"
   workflow_dispatch:
+    inputs:
+      job_filter:
+        description: 'Select which job to run (leave empty or "all" to run all jobs)'
+        required: false
+        type: choice
+        default: 'all'
+        options:
+          - 'all'
+          - 'nightly-test-general-1-gpu-runner'
+          - 'nightly-test-general-4-gpu-h100'
+          - 'nightly-test-general-8-gpu-h200'
+          - 'nightly-test-general-8-gpu-h20'
+          - 'nightly-test-text-accuracy-2-gpu-runner'
+          - 'nightly-test-text-perf-2-gpu-runner'
+          - 'nightly-test-vlm-accuracy-2-gpu-runner'
+          - 'nightly-test-vlm-perf-2-gpu-runner'
+          - 'nightly-test-multimodal-server-1-gpu'
+          - 'nightly-test-multimodal-server-2-gpu'
+          - 'nightly-test-perf-4-gpu-b200'
+          - 'nightly-test-perf-8-gpu-b200'
   workflow_call:
     inputs:
       ref:
         description: 'Git ref (branch, tag, or SHA) to test. If not provided, uses the default branch.'
         required: false
         type: string
         default: ''
+      job_filter:
+        description: 'Select which job to run (leave empty or "all" to run all jobs)'
+        required: false
+        type: string
+        default: 'all'
 
 concurrency:
   group: nightly-test-nvidia-${{ github.ref }}
@@ -24,11 +50,13 @@ concurrency:
 jobs:
   # General tests - 1 GPU
   nightly-test-general-1-gpu-runner:
-    if: github.repository == 'sgl-project/sglang'
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-1-gpu-runner')
     runs-on: 1-gpu-runner
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
 
       - name: Install dependencies
         run: |
@@ -38,15 +66,17 @@ jobs:
         timeout-minutes: 60
         run: |
           cd test
-          python3 run_suite_nightly.py --suite nightly-1-gpu --continue-on-error
+          python3 run_suite.py --hw cuda --suite nightly-1-gpu --nightly --continue-on-error
 
   # General tests - 4 GPU H100
   nightly-test-general-4-gpu-h100:
-    if: github.repository == 'sgl-project/sglang'
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-4-gpu-h100')
     runs-on: 4-gpu-h100
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
 
       - name: Install dependencies
         run: |
@@ -56,17 +86,19 @@ jobs:
         timeout-minutes: 30
         run: |
           cd test
-          python3 run_suite_nightly.py --suite nightly-4-gpu --continue-on-error
+          python3 run_suite.py --hw cuda --suite nightly-4-gpu --nightly --continue-on-error
 
   # General tests - 8 GPU H200
   nightly-test-general-8-gpu-h200:
-    if: github.repository == 'sgl-project/sglang'
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-8-gpu-h200')
     runs-on: 8-gpu-h200
     env:
       RUNNER_LABELS: 8-gpu-h200
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
 
       - name: Install dependencies
         run: |
@@ -78,7 +110,7 @@ jobs:
           GPU_CONFIG: "8-gpu-h200"
         run: |
           cd test
-          python3 run_suite_nightly.py --suite nightly-8-gpu-h200 --continue-on-error
+          python3 run_suite.py --hw cuda --suite nightly-8-gpu-h200 --nightly --continue-on-error
 
       - name: Run Qwen3-235B nightly performance test
         timeout-minutes: 180
@@ -158,13 +190,15 @@ jobs:
 
   # General tests - 8 GPU H20
   nightly-test-general-8-gpu-h20:
-    if: github.repository == 'sgl-project/sglang'
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-8-gpu-h20')
     runs-on: 8-gpu-h20
     env:
       SGLANG_CI_RDMA_ALL_DEVICES: "mlx5_1,mlx5_2,mlx5_3,mlx5_4"
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
 
       - name: Install dependencies
         run: |
@@ -176,15 +210,17 @@ jobs:
           GPU_CONFIG: "8-gpu-h20"
         run: |
           cd test
-          python3 run_suite_nightly.py --suite nightly-8-gpu-h20 --continue-on-error
+          python3 run_suite.py --hw cuda --suite nightly-8-gpu-h20 --nightly --continue-on-error
 
   # Text model accuracy tests
   nightly-test-text-accuracy-2-gpu-runner:
-    if: github.repository == 'sgl-project/sglang'
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-text-accuracy-2-gpu-runner')
     runs-on: 2-gpu-runner
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
 
       - name: Install dependencies
         run: |
@@ -198,11 +234,13 @@ jobs:
 
   # Text model performance tests
   nightly-test-text-perf-2-gpu-runner:
-    if: github.repository == 'sgl-project/sglang'
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-text-perf-2-gpu-runner')
     runs-on: 2-gpu-runner
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
 
       - name: Install dependencies
         run: |
@@ -229,11 +267,13 @@ jobs:
 
   # VLM accuracy tests
   nightly-test-vlm-accuracy-2-gpu-runner:
-    if: github.repository == 'sgl-project/sglang'
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-vlm-accuracy-2-gpu-runner')
     runs-on: 2-gpu-runner
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
 
       - name: Install dependencies
         run: |
@@ -247,11 +287,13 @@ jobs:
 
   # VLM performance tests
   nightly-test-vlm-perf-2-gpu-runner:
-    if: github.repository == 'sgl-project/sglang'
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-vlm-perf-2-gpu-runner')
     runs-on: 2-gpu-runner
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
 
       - name: Install dependencies
         run: |
@@ -278,7 +320,7 @@ jobs:
 
   # diffusion performance tests
   nightly-test-multimodal-server-1-gpu:
-    if: github.repository == 'sgl-project/sglang'
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-multimodal-server-1-gpu')
     runs-on: 1-gpu-runner
     strategy:
       fail-fast: false
@@ -288,6 +330,8 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
 
       - name: Install dependencies
         run: |
@@ -309,7 +353,7 @@ jobs:
 
 
   nightly-test-multimodal-server-2-gpu:
-    if: github.repository == 'sgl-project/sglang'
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-multimodal-server-2-gpu')
     runs-on: 2-gpu-runner
     strategy:
       fail-fast: false
@@ -319,6 +363,8 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
 
       - name: Install dependencies
         run: |
@@ -340,11 +386,13 @@ jobs:
 
   # B200 Performance tests - 4 GPU
   nightly-test-perf-4-gpu-b200:
-    if: github.repository == 'sgl-project/sglang'
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-perf-4-gpu-b200')
     runs-on: 4-gpu-b200
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
 
       - name: Install dependencies
         run: |
@@ -354,17 +402,19 @@ jobs:
         timeout-minutes: 60
         run: |
           cd test
-          python3 run_suite_nightly.py --suite nightly-4-gpu-b200 --continue-on-error
+          python3 run_suite.py --hw cuda --suite nightly-4-gpu-b200 --nightly --continue-on-error
 
   # B200 Performance tests - 8 GPU
   nightly-test-perf-8-gpu-b200:
-    if: github.repository == 'sgl-project/sglang'
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-perf-8-gpu-b200')
     runs-on: 8-gpu-b200
     env:
       RUNNER_LABELS: 8-gpu-b200
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
 
       - name: Install dependencies
         run: |

.github/workflows/pr-test-npu.yml

@@ -12,16 +12,8 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-
-  # ==================== PR Gate ==================== #
-  pr-gate:
-    uses: ./.github/workflows/pr-gate.yml
-    secrets: inherit
-  # ================================================= #
-
   # ==================== Check Changes ==================== #
   check-changes:
-    needs: [pr-gate]
     runs-on: ubuntu-latest
     outputs:
       main_package: ${{ steps.filter.outputs.main_package }}
@@ -40,10 +32,16 @@ jobs:
               - "scripts/ci/npu_ci_install_dependency.sh"
               - "test/srt/ascend/**"
               - ".github/workflows/pr-test-npu.yml"
-  # ======================================================= #
+
+  # ==================== PR Gate ==================== #
+  pr-gate:
+    needs: check-changes
+    if: needs.check-changes.outputs.main_package == 'true'
+    uses: ./.github/workflows/pr-gate.yml
+    secrets: inherit
 
   per-commit-1-npu-a2:
-    needs: [check-changes]
+    needs: [check-changes, pr-gate]
     if: needs.check-changes.outputs.main_package == 'true'
     runs-on: linux-arm64-npu-1
     container:
@@ -82,7 +80,7 @@ jobs:
           python3 run_suite.py --suite per-commit-1-npu-a2
 
   per-commit-2-npu-a2:
-    needs: [check-changes]
+    needs: [check-changes, pr-gate]
     if: needs.check-changes.outputs.main_package == 'true'
     runs-on: linux-arm64-npu-2
     strategy:
@@ -125,7 +123,7 @@ jobs:
           python3 run_suite.py --suite per-commit-2-npu-a2 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3
 
   per-commit-4-npu-a2:
-    needs: [check-changes]
+    needs: [check-changes, pr-gate]
     if: needs.check-changes.outputs.main_package == 'true'
     runs-on: linux-arm64-npu-4
     container:
@@ -164,7 +162,7 @@ jobs:
           python3 run_suite.py --suite per-commit-4-npu-a2 --timeout-per-file 3600
 
   per-commit-16-npu-a3:
-    needs: [check-changes]
+    needs: [check-changes, pr-gate]
     if: needs.check-changes.outputs.main_package == 'true'
     runs-on: linux-aarch64-a3-16
     strategy:

.github/workflows/pr-test-pd-router.yml

@@ -9,6 +9,7 @@ on:
       - 'sgl-router/**'
   pull_request:
     branches: [ main ]
+    types: [opened, synchronize, reopened, labeled]
     paths:
       - 'python/sglang/srt/disaggregation/**'
       - 'scripts/ci/ci_start_disaggregation_servers.sh'
@@ -26,7 +27,11 @@ permissions:
 
 jobs:
   test-disaggregation:
-    if: github.event_name != 'pull_request' || (contains(github.event.pull_request.labels.*.name, 'run-ci') && contains(github.event.pull_request.labels.*.name, 'router-benchmark'))
+    if: |
+      github.event_name != 'pull_request' ||
+      (github.event.action != 'labeled' && contains(github.event.pull_request.labels.*.name, 'run-ci') && contains(github.event.pull_request.labels.*.name, 'router-benchmark')) ||
+      (github.event.action == 'labeled' && github.event.label.name == 'run-ci' && contains(github.event.pull_request.labels.*.name, 'router-benchmark')) ||
+      (github.event.action == 'labeled' && github.event.label.name == 'router-benchmark' && contains(github.event.pull_request.labels.*.name, 'run-ci'))
     runs-on: [8-gpu-h200-oracle]
     timeout-minutes: 45