Skill rating

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

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 engine

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 specifi

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 method

Add or verify a model's chat prompt rendering and tokenization in rust/sglang-processor so it matches SGLang's Python serving path exactly (same prompt text, same token ids). Use when adding a model t

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 l

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 serv

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 computin

Naming conventions for SGLang speculative decoding identifiers. Use when adding, renaming, or reviewing identifiers in speculative decoding code — anything under `python/sglang/srt/speculative/`, rela

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 rev

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 relea

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

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 migrat

Apply the SGLang kernels RFC when adding, moving, splitting, or reviewing kernel APIs, registry metadata, kernel tests, benchmarks, and model-specific implementations. Use with add-jit-kernel, add-sgl

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

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

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

Audit SGLang startup logs, save evidence, and propose cleanup for user review. With no arguments, run Qwen3-8B at TP1 and TP2 plus gpt-oss-20b at TP1.

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

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.

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 / _playg

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

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

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/b

Workflow for upgrading/integrating cache-dit in SGLang diffusion (multimodal_gen): DBCache, DMD calibrator, TaylorSeer, SVDQuant DQ; porting upstream PRs and resolving conflicts against the per-reques

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

Guide to SGLang CI workflow orchestration — stage ordering, fail-fast, gating, partitioning, execution modes, and debugging CI failures. Use when modifying CI workflows, adding stages, debugging CI pi

Audit the existing test tree and CI configuration for improvements, using a catalog of patterns previously applied in this repo. Use when asked to audit tests or CI, shrink CI time or cost, find redun

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

Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang.kernels JIT infrastructure and public operator groups

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

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