sgl-project/sglang

1

add-sgl-kernel Step-by-step tutorial for adding a heavyweight AOT CUDA/C++ kernel to sgl-kernel (including tests & benchmarks)

sgl-project/sglang

39

2

debug-distributed-hang Debug hanging issues in SGLang distributed inference (TP/PP/DP/EP). Covers identifying hang locations via py-spy/watc…

sgl-project/sglang

13

3

sglang-prod-incident-triage Replay-first debug flow for SGLang serving problems.

sgl-project/sglang

13

4

debug-cuda-crash Call this skill when you need to debug CUDA crashes in SGLang using kernel API logging

sgl-project/sglang

12

5

add-jit-kernel Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang's jit_kernel module

sgl-project/sglang

11

6

llm-torch-profiler-analysis Unified LLM torch-profiler triage skill for `sglang`, `vllm`, `TensorRT-LLM`, and `TokenSpeed`. Use it to inspect an …

sgl-project/sglang

11

7

write-sglang-test Guide for writing SGLang CI/UT tests. Covers CustomTestCase, CI registration, server fixtures, model selection, mock …

sgl-project/sglang

11

8

clean-startup-log Clean up noisy startup warnings and spurious prints in SGLang server logs. Use when users ask to clean up unwanted wa…

sgl-project/sglang

10

9

cookbook-add-model Add a new model to the SGLang Cookbook (docs/, Mintlify), config-driven format — instantiate the model-agnostic templ…

sgl-project/sglang

10

10

generate-profile Generate an e2e profiling trace of an SGLang server run. Launches a server, validates accuracy, captures a Chrome-com…

sgl-project/sglang

10

11

ci-workflow-guide Guide to SGLang CI workflow orchestration — stage ordering, fast-fail, gating, partitioning, execution modes, and deb…

sgl-project/sglang

9

12

env-var-conventions Conventions for SGLang environment variables — where to define, how to access, how to name, and how to deprecate. Use…

sgl-project/sglang

9

13

sglang-bisect-ci-regression Investigate consistently failing SGLang CI tests by extracting the failure signature from scheduled or rerun workflow…

sgl-project/sglang

9

14

cookbook-migrate-model Migrate a legacy-template SGLang cookbook page (monolithic per-model generator under docs/src/snippets/autoregressive…

sgl-project/sglang

8

15

cookbook-review-pr Review a pull request against the SGLang Cookbook (docs/, Mintlify) contribution checklist — the config-driven format…

sgl-project/sglang

8

16

mechanical-refactor-verify Make mechanical refactoring (file splits, function moves, module extractions, renames) machine-checkable instead of e…

sgl-project/sglang

8

17

scripted-runtime-notes Requirements for the SGLang scripted runtime, chiefly when to add (vs not add) a harness API. Use for anything relate…

sgl-project/sglang

8

18

sglang-cherrypick Trigger the bot-cherry-pick workflow for a batch of merged PRs onto a release branch and monitor each run to completi…

sgl-project/sglang

8

19

speculative-naming Naming conventions for SGLang speculative decoding identifiers.

sgl-project/sglang

8

20

compute-mamba-ratio Compute the optimal --mamba-full-memory-ratio (or --max-mamba-cache-size pin) for a hybrid attention + linear-attenti…

sgl-project/sglang

3

21

kl-consistency-test Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent con…

sgl-project/sglang

2

22

large-class-init-style `__init__` style for SGLang `Scheduler`, `TokenizerManager`, and `ModelRunner`. Use when modifying the `__init__` of …

sgl-project/sglang

2

23

large-class-style Code style for SGLang large classes `Scheduler`, `TokenizerManager`, and `ModelRunner`: frozen-code conventions and `…

sgl-project/sglang

2

24

sglang-runtime-context How SGLang's runtime configuration and process-global state are organized (RuntimeContext tiers, publish + namespace …

sgl-project/sglang

2

25

sglang-sota-performance End-to-end SGLang SOTA performance workflow. Use when a user names an LLM model and wants SGLang to match or beat the…

sgl-project/sglang

2

26

babysit-pr-to-pass-ci Start and persistently pursue a goal to babysit an SGLang pull request until selected GitHub Actions workflows pass o…

sgl-project/sglang

1

27

llm-serving-auto-benchmark Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, or another serving framew…

sgl-project/sglang

1