스킬 찾기

Review existing tests and CI, the automated checks run during development, for redundant coverage, misplaced tests, and opportunities to reduce runtime or cost. Receive file-specific recommendations based on documented improvement patterns, with uncertain findings separated.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a slow test suite
• Finding redundant or misplaced tests
• Reviewing CI runtime and cost

Understand and modify SGLang's CI pipelines, including test stage order, start conditions, early stopping after failures, and workload splitting. Use the guide to add jobs and investigate failed, skipped, or cancelled checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add a test job to an SGLang CI stage
• Investigate failed or skipped CI checks
• Update test partitions and waiting job counts

Collect and review SGLang startup logs to identify unnecessary output and trace its source. Get saved logs and specific cleanup proposals while preserving useful diagnostics, with runtime changes left for user approval.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating repeated messages in startup logs
• Checking which startup warnings need attention
• Comparing startup logs across models and GPU counts

Add a model page to the SGLang Cookbook using shared templates. Organize verified launch settings and measured benchmarks, create configuration files and documentation, and update navigation, vendor cards, and page validation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add documentation for a newly supported model
• Organize verified launch recipes by hardware
• Publish measured speed and accuracy results

Add, rename, or review SGLang environment variables using consistent definitions, types, names, and access methods. The skill also guides migration from old names and temporary test overrides that restore the original values afterward.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a new SGLang environment variable
• Migrating deprecated environment variable names
• Temporarily overriding settings in tests

Guide changes and reviews for SGLang’s Scheduler, TokenizerManager, and ModelRunner classes. Keep initialization in small, replaceable helpers and separate computation from coordination so large classes retain clear responsibilities and explicit dependencies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing changes to SGLang’s three large classes
• Splitting initialization into replaceable helpers
• Moving computation out of ModelRunner

Verify file splits, function moves, module extractions, and renames by reproducing changes from a base commit and comparing files byte for byte. Generate repeatable proof scripts and reports that expose changes beyond relocation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Splitting a refactor into preparation, movement, and follow-up commits
• Generating repeatable proof scripts for code moves
• Verifying every provable commit in a branch

Investigate recurring SGLang automated test failures by comparing logs, commit history, and GPU environments. Narrow down code changes or machine-specific problems, optionally reproduce failures remotely, and summarize the evidence in a structured report.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding the change behind a recurring test failure
• Checking whether failures depend on a GPU or runner
• Reproducing a test failure on a remote GPU server

Attribute GPU time in one sglang-omni stage to specific lines of `sglang_omni/` python source. Drives the `llm-torch-profiler-analysis` backend with a mapping/formal trace pair plus steady-state gates, and carries the rules for reading its three tables on an omni stage. Use when a stage is slower than expected and the question is which python code is the bottleneck, not which kernel is hot.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generate 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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Run all reference benchmarks under benchmarks/eval/ and refresh the reference-table cells in benchmark_*.py. Auto-detects host hardware (H200/H100/H800/...). For each row's matching hw entry: replace cells in place. For new hardware or a new workload tag: append a new row to the section's table. Local-Pipeline-Result tables are skipped. One slash command runs everything end-to-end and auto-commits.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use 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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use 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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use 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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

RBG 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

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Implements 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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Step-by-step tutorial for adding a new lightweight SYCL JIT kernel for Intel XPU to sgl-kernel-xpu's python/sgl_kernel/jit module (SYCL source + Python wrapper + tests + benchmark)

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Upgrade 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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Add 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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audit 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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.