SGLang Agent Skills

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

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

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 infrastructural, auto-fix and push only small clean fixes, rerun failed jobs only up to 10 times, and ignore unselected workflows.

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.

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.

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 for a hybrid model.

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 /cookbook-add-model.

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 (use cookbook-add-model for those). Run with /cookbook-migrate-model <Model page name, e.g. GLM-5.1>.

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 <PR number>.

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

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 out during collective operations.

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`.

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.

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 divergence to a single operator. Use when adding a KL test to a model, picking or defending a kl_div threshold, or investigating a KL number that is too high.

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.

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.

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.

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

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.

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.

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 right next debug tool.

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 against it. Load this before touching server_args, model overrides, module-level state, or per-forward state in sglang.

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.

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 asks to add tests for SGLang features.

Use when adding a new diffusion model or Diffusers pipeline to SGLang.

Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.

Use when quantizing a diffusion DiT with NVIDIA ModelOpt and making the resulting FP8 or NVFP4 checkpoint loadable, verifiable, and benchmarkable in SGLang Diffusion.

Use when choosing the fastest SGLang Diffusion flags for a model, GPU, and VRAM budget.