인터페이스는 현지화되어 있으며, Skill 소개와 설명 문서는 선택한 언어로 AI가 자동 번역합니다. 코드·명령어·경로·전문 용어는 원문을 유지하며 원작자 문서가 우선합니다.
Skills 둘러보기
데이터 및 연구 · SKILL.md

benchmarking-profiling

benchmarking-profiling

Plan and analyze SGLang benchmarks, throughput/latency runs, profiling, request datasets, and reproducible performance triage.

Independent GitHub snapshot · Automated classification · Original documentation governs

Skill 문서

GitHub

name: benchmarking-profiling description: "Plan and analyze SGLang benchmarks, throughput/latency runs, profiling, request datasets, and reproducible performance triage." disable-model-invocation: true metadata: disco-role: operating license: Apache 2.0

Benchmarking Profiling

Use this sub-skill for bench_serving, bench_one_batch, auto_benchmark, profiler/NVTX workflows, concurrency/request-rate experiments, dataset selection, warmup policy, GPU metrics, and regression triage. Keep model, backend, commit, GPU, prompt lengths, output lengths, and traffic shape fixed before comparing results.

Cross-Links

  • Root routing: ../../SKILL.md
  • Workflow map: ../../references/workflow-map.md
  • Cross-cutting troubleshooting: ../../references/troubleshooting.md
저장한 Skills