Upstream sync 2026-05-25 (158 commits)

.claude/rules/modify-component-must-read.md

@@ -0,0 +1,6 @@
+# Must-Read Skills Before Modifying Components
+
+Before modifying the following components, read the listed skill first.
+
+- **Speculative decoding code** (anything under `python/sglang/srt/speculative/`, related attention backends, scheduler accumulators, IPC fields, observability metrics, or CLI flags) → [`speculative-naming`](../skills/speculative-naming/SKILL.md)
+- **`Scheduler` / `TokenizerManager` / `ModelRunner` `__init__`** (`python/sglang/srt/managers/scheduler.py`, `python/sglang/srt/managers/tokenizer_manager.py`, `python/sglang/srt/model_executor/model_runner.py`) → [`large-class-init-style`](../skills/large-class-init-style/SKILL.md)

.claude/skills/large-class-init-style/SKILL.md

@@ -0,0 +1,32 @@
+---
+name: large-class-init-style
+description: '`__init__` style for SGLang `Scheduler`, `TokenizerManager`, and `ModelRunner`. Use when modifying the `__init__` of any of these three classes, or reviewing changes that add new construction logic to them.'
+---
+
+# `__init__` Style for Scheduler / TokenizerManager / ModelRunner
+
+Apply when modifying the `__init__` of:
+
+- `Scheduler` — `python/sglang/srt/managers/scheduler.py`
+- `TokenizerManager` — `python/sglang/srt/managers/tokenizer_manager.py`
+- `ModelRunner` — `python/sglang/srt/model_executor/model_runner.py`
+
+## Why
+
+- Downstream forks override one piece (tokenizer, KV cache, IPC, …).
+- Inline logic forces them to copy the whole `__init__`, which rots against upstream.
+- Splitting into `init_*` helpers lets them override exactly what they need.
+- Reference shape: `TokenizerManager.__init__` in `python/sglang/srt/managers/tokenizer_manager.py`.
+
+## Rules
+
+- **`__init__` is an orchestrator.** Sequence of `self.init_*(...)` calls + minimal glue. No non-trivial construction inlined.
+- **One helper per overridable unit.** Each `init_*` = one concern a subclass might swap. Don't lump.
+- **Naming:** `init_<thing>` (snake_case, names the component). Conditional construction → `maybe_init_<thing>`, gate inside the helper.
+- **No silent state coupling.** A helper only reads `self.*` set by earlier helpers. Ordering lives in `__init__`. Shared intermediates → pass as args, not via `self.*`.
+- **New logic = new helper.** Default to adding `init_<thing>`, not another inline block. One-line `self.foo = server_args.foo` is fine; structured logic is not.
+- **Preserve override points.** Prefer additive changes to existing `init_*` signatures. Breaking changes → call out in PR.
+
+## Scope
+
+Only the three classes listed above. Not other manager-style classes, not small dataclass/utility constructors.

.claude/rules/speculative-naming.md → .claude/skills/speculative-naming/SKILL.md

@@ -1,6 +1,11 @@
+---
+name: speculative-naming
+description: Naming conventions for SGLang speculative decoding identifiers. Use when adding, renaming, or reviewing identifiers in speculative decoding code — anything under `python/sglang/srt/speculative/`, related attention backends, scheduler accumulators, IPC fields, observability metrics, or CLI flags.
+---
+
 # Speculative Decoding — Naming Conventions
 
-Apply this rule when adding, renaming, or reviewing identifiers in speculative decoding code (anything under `python/sglang/srt/speculative/`, related attention backends, scheduler accumulators, IPC fields, observability metrics, or CLI flags).
+Apply this skill when adding, renaming, or reviewing identifiers in speculative decoding code (anything under `python/sglang/srt/speculative/`, related attention backends, scheduler accumulators, IPC fields, observability metrics, or CLI flags).
 
 ## Rule 1 — Verb form, drop `-ed`
 

.codespellrc

@@ -1,3 +1,3 @@
 [codespell]
-ignore-words-list = ans, als, hel, boostrap, childs, te, vas, hsa, ment, cann, thi, makro, wil, rouge, PRIS, ather, MIS, medias, allready, inout, nd, fo, visibles, nothink, renderD, ond, tbe, CopyIn
+ignore-words-list = ans, als, hel, boostrap, childs, te, vas, hsa, ment, cann, thi, makro, wil, rouge, PRIS, ather, MIS, medias, allready, inout, nd, fo, visibles, nothink, renderD, ond, tbe, CopyIn, notin
 skip = *.json, *.jsonl, *.patch, *.txt, *.lock

.github/CI_PERMISSIONS.json

@@ -1399,6 +1399,13 @@
         "cooldown_interval_minutes": 0,
         "reason": "top contributor"
     },
+    "zianglih": {
+        "can_tag_run_ci_label": true,
+        "can_rerun_failed_ci": true,
+        "can_rerun_stage": true,
+        "cooldown_interval_minutes": 0,
+        "reason": "top contributor"
+    },
     "zminglei": {
         "can_tag_run_ci_label": true,
         "can_rerun_failed_ci": true,

.github/CODEOWNERS

@@ -1,6 +1,6 @@
 .github @merrymercy @Fridge003 @ispobock @Kangyan-Zhou @bingxche
 /docker @Fridge003 @ispobock @HaiShaw @ishandhanani @yctseng0211
-/docker/npu.Dockerfile @ping1jing2 @iforgetmyname
+/docker/npu.Dockerfile @ping1jing2 @iforgetmyname @whybeyoung
 /docs @wisclmy0611 @zijiexia
 /docs_new @wisclmy0611 @zijiexia @Richardczl98 @JustinTong0323
 /python/pyproject.toml @merrymercy @Fridge003 @ispobock
@@ -29,7 +29,7 @@
 /python/sglang/srt/grpc @CatherineSue @slin1237
 /python/sglang/srt/hardware_backend/mlx @yeahdongcn
 /python/sglang/srt/hardware_backend/musa @yeahdongcn
-/python/sglang/srt/hardware_backend/npu @ping1jing2 @iforgetmyname
+/python/sglang/srt/hardware_backend/npu @ping1jing2 @iforgetmyname @whybeyoung
 /python/sglang/srt/hardware_backend/npu/quantization @OrangeRedeng @TamirBaydasov @iforgetmyname
 /python/sglang/srt/layers @merrymercy @Ying1123 @Fridge003 @ispobock @HaiShaw @ch-wan @BBuf @Edwardf0t1
 /python/sglang/srt/layers/attention @merrymercy @Fridge003 @ispobock @Qiaolin-Yu @hebiao064 @HaiShaw
@@ -45,13 +45,16 @@
 /python/sglang/srt/managers/scheduler_pp_mixin.py @ShangmingCai @XucSh
 /python/sglang/srt/managers/tokenizer_manager_score_mixin.py @sundar24295s @chanh @fortunecookiee
 /python/sglang/srt/mem_cache @merrymercy @Ying1123 @hnyls2002 @xiezhq-hermann @hanming-lu @yizhang2077 @hzh0425 @ispobock
+/python/sglang/srt/mem_cache/storage/mooncake_store/embedding_cache_controller.py @liusy58
+/python/sglang/srt/mem_cache/storage/mooncake_store/mooncake_embedding_store.py @liusy58
 /python/sglang/srt/model_executor @merrymercy @Ying1123 @hnyls2002 @Fridge003 @ispobock
 /python/sglang/srt/model_executor/piecewise_cuda_graph_runner.py @hebiao064
 /python/sglang/srt/models/deepseek_common @Fridge003 @ispobock @fzyzcjy @ch-wan
 /python/sglang/srt/models/deepseek_v2.py @fzyzcjy @zhyncs @ispobock @ch-wan @merrymercy @Fridge003
 /python/sglang/srt/models/transformers.py @adarshxs
 /python/sglang/srt/multimodal @mickqian @JustinTong0323 @yhyang201 @yuan-luo
 /python/sglang/srt/observability @merrymercy @fzyzcjy @sufeng-buaa
+/python/sglang/srt/platforms @merrymercy @whybeyoung
 /python/sglang/srt/ray @Qiaolin-Yu @xyuzh
 /python/sglang/srt/speculative @Ying1123 @merrymercy @hnyls2002 @Qiaolin-Yu
 /sgl-kernel @ispobock @BBuf @yizhang2077 @merrymercy @FlamingoPg @HaiShaw

.github/actions/upload-cuda-coredumps/action.yml

@@ -1,5 +1,5 @@
 name: Upload CUDA Coredumps
-description: Upload CUDA coredump files as artifacts and clean up the directory.
+description: Upload CUDA coredump files as artifacts, optionally signal to a tracker issue, and clean up.
 
 inputs:
   artifact-suffix:
@@ -10,17 +10,75 @@ inputs:
     description: Number of days to retain the artifact
     required: false
     default: "7"
+  tracker-issue:
+    description: |
+      If set, post a one-line comment to sgl-project/sglang issue
+      #<tracker-issue> when at least one coredump is detected. Requires
+      `bot-token` with issues:write on sgl-project/sglang.
+    required: false
+    default: ""
+  bot-token:
+    description: PAT with issues:write on sgl-project/sglang. Required when tracker-issue is set.
+    required: false
+    default: ""
 
 runs:
   using: composite
   steps:
+    - name: Check for coredumps
+      id: check
+      shell: bash
+      run: |
+        dir="${SGLANG_CUDA_COREDUMP_DIR:-/tmp/sglang_cuda_coredumps}"
+        if [ -d "$dir" ] && [ -n "$(ls -A "$dir" 2>/dev/null)" ]; then
+          echo "has_dumps=true" >> "$GITHUB_OUTPUT"
+        else
+          echo "has_dumps=false" >> "$GITHUB_OUTPUT"
+        fi
+
     - name: Upload CUDA coredumps
+      if: steps.check.outputs.has_dumps == 'true'
       uses: actions/upload-artifact@v4
       with:
         name: cuda-coredumps-${{ github.job }}${{ inputs.artifact-suffix && format('-{0}', inputs.artifact-suffix) }}
         path: ${{ env.SGLANG_CUDA_COREDUMP_DIR || '/tmp/sglang_cuda_coredumps' }}/
         retention-days: ${{ inputs.retention-days }}
-        if-no-files-found: ignore
+
+    - name: Signal coredump to tracker issue
+      if: steps.check.outputs.has_dumps == 'true' && inputs.tracker-issue != '' && inputs.bot-token != ''
+      shell: bash
+      env:
+        BOT_TOKEN: ${{ inputs.bot-token }}
+        PR_NUM: ${{ github.event.pull_request.number }}
+        EVENT_NAME: ${{ github.event_name }}
+        TRACKER_ISSUE: ${{ inputs.tracker-issue }}
+      run: |
+        if [ -n "$PR_NUM" ]; then
+          ref_label="PR #${PR_NUM}"
+        else
+          ref_label="$EVENT_NAME"
+        fi
+        # Resolve own job_id via REST API: match by runner_name + status
+        # in_progress (the current job is the only one in_progress on this
+        # runner). Robust across matrix expansions and artifact-suffix shapes.
+        job_id=$(curl -sS \
+          -H "Authorization: Bearer ${BOT_TOKEN}" \
+          -H "Accept: application/vnd.github+json" \
+          "${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/attempts/${GITHUB_RUN_ATTEMPT}/jobs?per_page=100" \
+          | python3 -c 'import json,sys,os; print(next((j["id"] for j in json.load(sys.stdin)["jobs"] if j.get("runner_name")==os.environ["RUNNER_NAME"] and j.get("status")=="in_progress"), ""))')
+        if [ -n "$job_id" ]; then
+          run_url="${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/job/${job_id}"
+        else
+          # Fallback to run-attempt URL if job_id lookup failed
+          run_url="${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/attempts/${GITHUB_RUN_ATTEMPT}"
+        fi
+        body_json=$(printf '{"body":"@hnyls2002 [Coredump Tracker] %s - %s"}' "${ref_label}" "${run_url}")
+        curl -sS -X POST \
+          -H "Authorization: Bearer ${BOT_TOKEN}" \
+          -H "Accept: application/vnd.github+json" \
+          -H "X-GitHub-Api-Version: 2022-11-28" \
+          "https://api.github.com/repos/sgl-project/sglang/issues/${TRACKER_ISSUE}/comments" \
+          -d "${body_json}"
 
     - name: Cleanup CUDA coredumps
       shell: bash

.github/workflows/_pr-test-stage.yml

@@ -171,6 +171,8 @@ jobs:
         if: failure()
         with:
           artifact-suffix: ${{ matrix.partition }}
+          tracker-issue: "26340"
+          bot-token: ${{ secrets.GH_PAT_FOR_PULL_REQUEST }}
 
       - name: Cleanup venv
         if: always()

.github/workflows/bot-cherry-pick.yml

@@ -20,15 +20,10 @@ permissions:
   contents: write
   pull-requests: write
 
-concurrency:
-  group: cherry-pick-${{ github.event.inputs.target_branch }}
-  cancel-in-progress: false
-
 jobs:
   cherry-pick:
     if: github.repository == 'sgl-project/sglang'
     runs-on: ubuntu-latest
-    environment: 'prod'
     steps:
       - name: Validate inputs
         env:

.github/workflows/cancel-pr-workflow-on-merge.yml

@@ -1,4 +1,4 @@
-name: Cancel PR Workflows on Merge
+name: Cancel PR Workflows on Close
 
 on:
   pull_request_target:
@@ -10,7 +10,6 @@ permissions:
 
 jobs:
   cancel:
-    if: github.event.pull_request.merged == true
     runs-on: ubuntu-latest
     steps:
       - name: Cancel Previous Runs