sgl-project
- 28 skills
- 0 followers
- 12 hours ago last updated
- ▌ Stress Test · sgl-project bundleRBG controller stress test - deploy kwok in existing cluster, run create/update/delete load tests with real controller pod, collect pprof profiling and logs, generate analysis report with recommendations
- ▌ Planning With Files · sgl-project bundleImplements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring >5 tool calls. Supports automatic session recovery after /clear.
- ▌ Add Model · sgl-projectAdd a new model to the SGLang Cookbook, including documentation, sidebar, config generator component, and model YAML configuration.
- ▌ Review Pr · sgl-projectReview a pull request against the cookbook contribution checklist. Run with /review-pr <PR number>.
- ▌ Model Profiling · sgl-project bundleGenerate a bounded task plan (and the agent prompt for it) that runs the 5-layer profiling methodology in .claude/skills/model-profiling/METHODOLOGY.md against one model, stops for human confirmation before any GPU work starts, then delegates the actual run to a background agent, verifies its completion claim, and routes findings into a gitignored .profiling-runs/<model>/ directory — durably tracked as a sub-issue under the tracking issue named in SKILL.md's "Result tracking" section — plus the methodology doc.
- ▌
- ▌ Add Benchmark · sgl-projectAdd a new benchmark to sgl-eval by vendoring its NeMo-Skills dataset module and registering it in `_TABLE`. Use when the user asks to "add <benchmark>" / "support <benchmark>" / "register <benchmark>" inside the sgl-eval repo.
- ▌ Vendor Update · sgl-projectUpgrade the vendored NeMo-Skills slice to a newer upstream commit. Use when the user asks to "bump vendored", "sync NeMo-Skills", "update vendored sha", "upgrade NS", or wants to pull a specific upstream fix. Inside the sgl-eval repo.
- ▌ Review Vendor Coverage · sgl-projectAudit whether all score-deciding logic in sgl-eval is vendored from NeMo-Skills, or whether some has crept into SE code. Use when the user asks "are we vendoring enough", "review vendor coverage", "audit vendoring", "is our vendoring complete", or before a release.
- ▌ Profiling Capture · sgl-project bundleUse when you need to CAPTURE / PRODUCE XProf (jax.profiler) profiling artifacts from sgl-jax (SGLang on JAX/TPU) for later performance analysis: driving a live server (/start_profile, stage-separated prefill/decode), offline bench_one_batch --profile, or kernel microbench. This skill produces the trace files; it does not analyze them.
- ▌ Model Speed Benchmark · sgl-project bundleUse when running throughput/latency (serving speed) benchmarks against an already-running model server. Uses sgl_jax.bench_serving to sweep batch-size/concurrency and measure throughput and latency, producing summary.csv and per-point bs_<N>/result.jsonl. Speed only — accuracy/eval belongs to model-accuracy-benchmark. Triggers on throughput, latency, bench_serving, batch-size sweep, tok/s, TTFT, TPOT — not accuracy/eval.
- ▌ Model Accuracy Benchmark · sgl-project bundleUse when evaluating a newly adapted model's accuracy/eval score. Runs evalscope eval (or the test/srt/run_eval.py fallback) against an OpenAI-compatible endpoint on datasets like gsm8k / aime, producing per-dataset reports and a score. Accuracy only — throughput/latency benchmarks belong to model-speed-benchmark. Triggers on accuracy, eval, evalscope, gsm8k, aime, run_eval — not throughput.
- ▌ Babysit Pr To Pass CI · sgl-projectStart 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.
- ▌ Compute Mamba Ratio · sgl-projectCompute 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.
- ▌ Env Var Conventions · sgl-projectConventions 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`.
- ▌ Kl Consistency Test · sgl-projectWrite, 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.
- ▌ Cookbook Add Model · sgl-projectAdd 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.
- ▌ Cookbook Review Pr · sgl-projectReview 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>.
- ▌ Speculative Naming · sgl-projectNaming 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.
- ▌ CI Workflow Guide · sgl-projectGuide 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 Startup Log · sgl-projectClean 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.
- ▌ Large Class Style · sgl-projectCode 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.
- ▌ Sglang Cherrypick · sgl-projectTrigger 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.
- ▌ Write Sglang Test · sgl-projectGuide 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.
- ▌ Debug Cuda Crash · sgl-projectCall this skill when you need to debug CUDA crashes in SGLang using kernel API logging
- ▌ Generate Profile · sgl-projectGenerate an e2e profiling trace of an SGLang server run. Launches a server, validates accuracy, captures a Chrome-compatible trace, and returns the profile path.
- ▌ Add Jit Kernel · sgl-projectStep-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang's jit_kernel module
- ▌ Add Sgl Kernel · sgl-projectStep-by-step tutorial for adding a heavyweight AOT CUDA/C++ kernel to sgl-kernel (including tests & benchmarks)