Update docs (#13391)

Co-authored-by: sglang-bot <sglangbot@gmail.com>

.github/CODEOWNERS

@@ -1,28 +1,26 @@
-.github @merrymercy @Fridge003 @ispobock
-/docker @Fridge003 @ispobock @HaiShaw @ByronHsu
-/docker/npu.Dockerfile @ping1jing2
+.github @merrymercy @Fridge003 @ispobock @Kangyan-Zhou
+/docker @Fridge003 @ispobock @HaiShaw @ishandhanani
+/docker/npu.Dockerfile @ping1jing2 @iforgetmyname
 /python/pyproject.toml @merrymercy @Fridge003 @ispobock
-/python/sglang/* @merrymercy @Ying1123 @Fridge003 @ispobock @hnyls2002
 /python/sglang/multimodal_gen @mickqian
-/python/sglang/srt/constrained @hnyls2002
-/python/sglang/srt/disaggregation @ByronHsu @hnyls2002
-/python/sglang/srt/disaggregation/mooncake @ShangmingCai
-/python/sglang/srt/disaggregation/ascend @ping1jing2
-/python/sglang/srt/distributed @yizhang2077 @merrymercy
+/python/sglang/srt/constrained @hnyls2002 @DarkSharpness
+/python/sglang/srt/disaggregation @ByronHsu @hnyls2002 @ShangmingCai
+/python/sglang/srt/disaggregation/ascend @ping1jing2 @iforgetmyname
+/python/sglang/srt/distributed @yizhang2077 @merrymercy @ch-wan
 /python/sglang/srt/entrypoints @ispobock @CatherineSue @slin1237 @merrymercy @JustinTong0323
-/python/sglang/srt/eplb @fzyzcjy
+/python/sglang/srt/eplb @fzyzcjy @ch-wan
 /python/sglang/srt/function_call @CatherineSue @JustinTong0323
 /python/sglang/srt/layers @merrymercy @Ying1123 @Fridge003 @ispobock @HaiShaw @ch-wan @BBuf @kushanam @Edwardf0t1
-/python/sglang/srt/layers/quantization @ch-wan @BBuf @Edwardf0t1 @FlamingoPg
-/python/sglang/srt/layers/attention/ascend_backend.py @ping1jing2
+/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
-/python/sglang/srt/managers @merrymercy @Ying1123 @zhyncs @hnyls2002 @xiezhq-hermann
+/python/sglang/srt/managers @merrymercy @Ying1123 @hnyls2002 @xiezhq-hermann @zhyncs
 /python/sglang/srt/mem_cache @merrymercy @Ying1123 @hnyls2002 @xiezhq-hermann
-/python/sglang/srt/mem_cache/allocator_ascend.py @ping1jing2
+/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
-/python/sglang/srt/multimodal @mickqian @JustinTong0323
-/python/sglang/srt/speculative @Ying1123 @merrymercy @kssteven418
+/python/sglang/srt/model_executor/npu_graph_runner.py @ping1jing2 @iforgetmyname
+/python/sglang/srt/multimodal @mickqian @JustinTong0323 @yhyang201
+/python/sglang/srt/speculative @Ying1123 @merrymercy @hnyls2002
 /sgl-kernel @zhyncs @ispobock @BBuf @yizhang2077 @merrymercy @FlamingoPg @HaiShaw
 /sgl-router @slin1237 @ByronHsu @CatherineSue
 /sgl-router/benches @slin1237
@@ -40,5 +38,5 @@
 /sgl-router/src/routers @CatherineSue @key4ng @slin1237
 /sgl-router/src/tokenizer @slin1237 @CatherineSue
 /sgl-router/src/tool_parser @slin1237 @CatherineSue
+/test/srt/ascend @ping1jing2 @iforgetmyname
 /test/srt/test_modelopt* @Edwardf0t1
-/test/srt/ascend @ping1jing2

.github/ISSUE_TEMPLATE/1-bug-report.yml

@@ -1,5 +1,5 @@
 name: 🐞 Bug report
-description: Create a report to help us reproduce and fix the bug
+description: Report a bug to help us reproduce and fix it.
 title: "[Bug] "
 labels: ['Bug']
 
@@ -8,31 +8,28 @@ body:
   attributes:
     label: Checklist
     options:
-    - label: 1. I have searched related issues but cannot get the expected help.
-    - label: 2. The bug has not been fixed in the latest version.
-    - label: 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
-    - label: 4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.
-    - label: 5. Please use English, otherwise it will be closed.
+      - label: I searched related issues but found no solution.
+      - label: The bug persists in the latest version.
+      - label: Issues without environment info and a minimal reproducible demo are hard to resolve and may receive no feedback.
+      - label: If this is not a bug report but a general question, please start a discussion at https://github.com/sgl-project/sglang/discussions. Otherwise, it will be closed.
+      - label: Please use English. Otherwise, it will be closed.
 - type: textarea
   attributes:
     label: Describe the bug
-    description: A clear and concise description of what the bug is.
+    description: A clear, concise description of the bug.
   validations:
     required: true
 - type: textarea
   attributes:
     label: Reproduction
-    description: |
-      What command or script did you run? Which **model** are you using?
-    placeholder: |
-      A placeholder for the command.
+    description: Command/script run and model used.
+    placeholder: Paste the command here.
   validations:
     required: true
 - type: textarea
   attributes:
     label: Environment
-    description: |
-      Please provide necessary environment information here with `python3 -m sglang.check_env`. Otherwise the issue will be closed.
-    placeholder: Environment here.
+    description: Run `python3 -m sglang.check_env` and paste output here. Issues without this will be closed.
+    placeholder: Paste environment output here.
   validations:
     required: true

.github/ISSUE_TEMPLATE/2-feature-request.yml

@@ -7,17 +7,17 @@ body:
   attributes:
     label: Checklist
     options:
-    - label: 1. If the issue you raised is not a feature but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.
-    - label: 2. Please use English, otherwise it will be closed.
+      - label: If this is not a feature request but a general question, please start a discussion at https://github.com/sgl-project/sglang/discussions. Otherwise, it will be closed.
+      - label: Please use English. Otherwise, it will be closed.
 - type: textarea
   attributes:
     label: Motivation
     description: |
-      A clear and concise description of the motivation of the feature.
+      Clearly and concisely describe the feature's motivation.
   validations:
     required: true
 - type: textarea
   attributes:
     label: Related resources
     description: |
-      If there is an official code release or third-party implementations, please also provide the information here, which would be very helpful.
+      Provide official releases or third-party implementations if available.

.github/MAINTAINER.md

@@ -0,0 +1,40 @@
+# SGLang Code Maintenance Model
+This documentation describes the code maintenance model for the SGLang project.
+Since SGLang is a large project involving multiple organizations and hardware platforms, we designed this model with the following goals:
+- Ensure a responsive and smooth review process.
+- Allow fast iteration, so maintainers can sometimes bypass flaky CI tests for important PRs.
+
+## Role Descriptions
+There are four important roles in this maintenance model. Some are custom roles, while the others are roles predefined by GitHub.
+
+- *Area Maintainer*: The person who drives the PR merge process. They have strong area expertise and hold a high code quality bar.
+  - Permission: Merge PRs. Bypass branch protection rules if needed.
+  - Responsibility: Shepherd the merge of PRs assigned to your area. Revert or hotfix any issues related to your merge (especially if you bypass).
+- *Codeowner*: The person who protects critical code. Without bypass, each PR needs at least one Codeowner approval for each modified file. Please note that this role is not an honor but a great responsibility because PRs cannot be merged without your approval (except when bypassed by an Area Maintainer).
+  - Permission: Approve PRs, allowing them to be merged without bypass.
+  - Responsibility: Review PRs in a timely manner.
+- *Write*: The person with write permission to the sglang repo.
+  - Permission: Merge PRs if they have passed required tests and been approved by Codeowners. This role cannot bypass branch protection rules.
+  - Responsibility: Review and merge PRs in a timely manner.
+- *CI Maintainer*: The person who manages CI runners for specific hardware platforms.
+  - Permission: Add CI runners.
+  - Responsibility: Keep the CI runners up and running.
+
+Note: Difference between Area Maintainer and Codeowner
+- Area Maintainer is an active role who actively try to help merge PRs and can bypass CI if urgent.
+- Codeowner is a passive protection rule provided by GitHub; it prevents accidental changes to critical code.
+- The list of Area Maintainer is attached below. The list of Codeowner is in [CODEOWNERS](./CODEOWNERS) file.
+
+## Pull Request Merge Process
+1. Author submits a pull request (PR) and fills out the PR checklist.
+2. A bot assigns this PR to an Area Maintainer and @-mention them. At the same time, GitHub will auto-request reviews from Codeowners.
+3. The Area Maintainer coordinates the review (asking people to review) and approves the PR; the Codeowner approves the PR.
+4. We can now merge the code:
+   - Ideal case: For each modified file, one Codeowner approves the PR. It also passes the required CI. Then anyone with write permission can merge the code.
+   - In cases where it is difficult to meet all requirements due to flaky CI or slow responses, an Area Maintainer can bypass branch protection to merge the PR.
+
+## The List of Area Maintainers and Reviewers
+TODO
+
+## The List of CI Maintainers
+TODO

.github/REVIEWERS.md

@@ -1,54 +0,0 @@
-# Area Reviewer
-
-Here are some reviewers for common areas. You can ping them to review your code if you touch related parts.
-
-## Hardware platforms
-- general @Alcanderian
-- AMD GPU @HaiShaw
-- Blackwell GPU @kushanam @trevor-m @zhyncs
-- CPU @mingfeima
-
-## Kernel
-- general @zhyncs @ispobock @HandH1998 @BBuf @yizhang2077 @HaiShaw
-- triton attention backend @ispobock
-- aiter attention backend @HaiShaw @kkHuang-amd @valarLip
-- flash attention backend @hebiao064
-- flashinfer attention backend @Fridge003
-- moe kernel @BBuf @fzyzcjy @ch-wan @Alcanderian
-- quantization @FlamingoPg @HandH1998
-
-## Scheduler and memory pool
-- general @merrymercy @Ying1123 @hnyls2002 @xiezhq-hermann
-- constrained decoding @hnyls2002
-- hierarchical cache @xiezhq-hermann @DarkSharpness
-- lora @Fridge003 @Ying1123 @lifuhuang
-- speculative decoding @merrymercy @Ying1123 @kssteven418 @Qiaolin-Yu
-- sliding window attention @hanming-lu
-
-## Parallelism
-- expert parallelism @fzyzcjy @ch-wan
-- data parallelism attention @ch-wan
-- pipeline parallelism @Ying1123
-- tensor parallelism @merrymercy
-
-## PD disaggregation
-- general @ByronHsu @ShangmingCai @hnyls2002
-- Mooncake backend @ShangmingCai
-
-## Build and release
-- general @zhyncs @merrymercy
-
-## API Server
-- general @CatherineSue @slin1237 @ispobock
-- function calling and reasoning parsing @CatherineSue
-- OpenAI API @CatherineSue @slin1237
-
-## SGL-Router
-- general @slin1237 @ByronHsu
-
-## Model
-- multimodal models @mickqian @JustinTong0323
-- other new models @zhaochenyang20
-
-## Reinforcment learning
-- general @zhaochenyang20 @hebiao064 @fzyzcjy @zhuzilin

.github/labeler.yml

@@ -26,7 +26,7 @@ dependencies:
       - '**/requirements*.txt'
       - '**/Cargo.toml'
       - '**/Cargo.lock'
-      - '**/pyproject.toml'
+      - '**/pyproject*.toml'
       - '**/setup.py'
       - '**/poetry.lock'
       - '**/package.json'
@@ -36,31 +36,27 @@ dependencies:
 Multi-modal:
   - changed-files:
     - any-glob-to-any-file:
-      - '**/vision/**/*'
-      - '**/multimodal/**/*'
-      - '**/vlm/**/*'
+      - '**/*multimodal*'
+      - '**/*vision*'
+      - '**/*vlm*'
 
 # LoRA
 lora:
   - changed-files:
     - any-glob-to-any-file:
-      - '**/lora/**/*'
       - '**/*lora*'
 
 # Quantization
 quant:
   - changed-files:
     - any-glob-to-any-file:
-      - '**/quant/**/*'
       - '**/*quant*'
-      - '**/awq/**/*'
-      - '**/gptq/**/*'
+      - '**/*quantization*'
 
 # Speculative decoding
 speculative-decoding:
   - changed-files:
     - any-glob-to-any-file:
-      - '**/speculative/**/*'
       - '**/*speculative*'
 
 # AMD specific
@@ -80,5 +76,4 @@ deepseek:
 hicache:
   - changed-files:
     - any-glob-to-any-file:
-      - '**/hicache/**/*'
       - '**/*hicache*'

.github/workflows/lint.yml

@@ -9,6 +9,7 @@ on:
 jobs:
   lint:
     runs-on: ubuntu-latest
+    if: contains(github.event.pull_request.labels.*.name, 'run-ci')
     steps:
       - uses: actions/checkout@v4