sgl-project

sgl-project/sglang

Skill Claude CodeCodex

Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang's jitkernel module.

sgl-project/sglang

Skill Claude CodeCodex

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

sgl-project/sglang

Skill Claude CodeCodex

Start and persistently pursue a goal to babysit an SGLang pull request until selected GitHub Actions workflows pass on the latest PR head. Use when asked to monitor, babysit, retry, or fix PR CI for lint.yml, pr-test.yml, pr-test-extra.yml, AMD, or other named workflows; classify failures as PR-related versus flaky or…

sgl-project/sglang

Skill Claude CodeCodex

Guide to SGLang CI workflow orchestration — stage ordering, fast-fail, gating, partitioning, execution modes, and debugging CI failures. Use when modifying CI workflows, adding stages, debugging CI pipeline issues, or understanding how tests are dispatched and gated across stages.

sgl-project/sglang

Skill Claude CodeCodex

Clean up noisy startup warnings and spurious prints in SGLang server logs. Use when users ask to clean up unwanted warnings, deprecation messages, or third-party noise in the server startup output.

sgl-project/sglang

Skill Claude CodeCodex

Compute the optimal --mamba-full-memory-ratio (or --max-mamba-cache-size pin) for a hybrid attention + linear-attention (Mamba / GDN / KDA) model's two serving memory pools, from the workload and serving config. Use when a user asks what ratio to set, why concurrency is clamped, or how to size the state vs KV pools…

sgl-project/sglang

Skill Claude CodeCodex

Add a new model to the SGLang Cookbook (docs/, Mintlify), config-driven format — instantiate the model-agnostic template into a per-model config (+ benchmarks) JSX under src/snippets/configs/, an MDX page, the docs.json nav entry, NEW-tag hygiene, and the homepage vendor card. Interactive, multi-phase. Run with…

sgl-project/sglang

Skill Claude CodeCodex

Migrate a legacy-template SGLang cookbook page (monolithic per-model generator under docs/src/snippets/autoregressive/) onto the config-driven template (shared deployment.jsx / playground.jsx engines + per-model config). Use when asked to migrate, convert, or port an existing cookbook page — NOT for brand-new models…

sgl-project/sglang

Skill Claude CodeCodex

Review a pull request against the SGLang Cookbook (docs/, Mintlify) contribution checklist — the config-driven format (per-model config + benchmarks JSX consumed by the shared deployment.jsx / playground.jsx engines). Run with /cookbook-review-pr .

sgl-project/sglang

Skill Claude CodeCodex

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

sgl-project/sglang

Skill Claude CodeCodex

Debug hanging issues in SGLang distributed inference (TP/PP/DP/EP). Covers identifying hang locations via py-spy/watchdog/cuda coredump, per-rank logging to find state divergence, binary-search methodology for locating the first diverge point, and fix patterns. Use when a multi-GPU SGLang run hangs, freezes, or times…

sgl-project/sglang

Skill Claude CodeCodex

Conventions for SGLang environment variables — where to define, how to access, how to name, and how to deprecate. Use when adding, renaming, or reviewing any SGLANG environment variable (or migrating a legacy SGL alias), or when touching python/sglang/srt/environ.py.

sgl-project/sglang

Skill Claude CodeCodex

Generate an e2e profiling trace of an SGLang server run. Launches a server, validates accuracy, captures a Chrome-compatible trace, and returns the profile path.

sgl-project/sglang

Skill Claude CodeCodex

Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths computing the same function), which helper separates them, how to pick a threshold once they hold, and how to localize a…

sgl-project/sglang

Skill Claude CodeCodex

Code style for SGLang large classes Scheduler, TokenizerManager, and ModelRunner: frozen-code conventions and init orchestration style. Use when modifying any of these three classes or reviewing changes to them.

sgl-project/sglang

Skill Claude CodeCodex

Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed. Use it to inspect an existing trace.json(.gz) or profile directory, or to drive live profiling against a running server when supported and return one three-table report with kernel, overlap-opportunity, and fuse-pattern tables.

sgl-project/sglang

Skill Claude CodeCodex

Make mechanical refactoring (file splits, function moves, module extractions, renames) machine-checkable instead of eyeballed. Reproduce a relocation commit byte-for-byte from faithful primitives, and split an extraction into a verifiable prepare + move + postpare. Use when doing or reviewing such changes.

sgl-project/sglang

Skill Claude CodeCodex

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

sgl-project/sglang

Skill Claude CodeCodex

Investigate consistently failing SGLang CI tests by extracting the failure signature from scheduled or rerun workflows, bisecting the passing/failing commit window, checking runner or hardware specificity, and optionally reproducing on a remote GPU host.

sgl-project/sglang

Skill Claude CodeCodex

Trigger the bot-cherry-pick workflow for a batch of merged PRs onto a release branch and monitor each run to completion. Use when an SGLang release manager asks to cherry-pick a list of PRs to a release branch.

sgl-project/sglang

Skill Claude CodeCodex

Replay-first debug flow for SGLang serving problems. Use when a live or recent server shows health-check failures, latency or throughput regressions, queue growth, timeouts, distributed stalls, crash dumps, wrong outputs after deploys, or PD/EP/HiCache issues, and the job is to turn the problem into a replay plus the…

sgl-project/sglang

Skill Claude CodeCodex

How SGLang's runtime configuration and process-global state are organized (RuntimeContext tiers, publish + namespace config bags, the pristine ServerArgs seed, override entry points, resource/stream/buffer leases, per-forward flags), the CI guardrails that enforce the design, and the idioms for developing and testing…

sgl-project/sglang

Skill Claude CodeCodex

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.

sgl-project/sglang

Skill Claude CodeCodex

Guide for writing SGLang CI/UT tests. Covers CustomTestCase, CI registration, server fixtures, model selection, mock testing, and test placement. Always read test/README.md for the full CI layout, how to run tests, and extra tips. Use when creating new tests, adding CI test cases, writing unit tests, or when the user…