Опишете задачата
Към всички skills

perfup

raullenchai · Данни и AI

Autonomous performance optimization: research, PoC, benchmark, implement, review, PR

Оригинален текст · няма потвърден превод на български
Платформи: Не са посочениНиво: Не е посоченоВ индекса: 21.09.2026 г.Обновен в GitHub: 21.09.2026 г.

Теми: apple-silicon · claude-code · cursor · deepseek · fastapi · hacktoberfest · inference · llm · local-llm · m1 · m2 · m3 · macos · mlx · ollama-alternative

Първо прочетете инструкцията.

Файлът се зарежда от посочения източник само по ваше действие. Можете да го прочетете тук, да го копирате или да го запазите като .md.

Оригинален SKILL.md
GitHub хранилище
Звезди на репото
3821
Лиценз
NOASSERTION
Последна проверка на записа
22.09.2026 г.

Добавете в своя инструмент.

Командата отваря избора на skills от репозитория. Прочетете файла и условията на автора преди изпълнение.

npx skills add raullenchai/Rapid-MLX

Страницата копира текст. Не инсталира и не изпълнява нищо на устройството ви.

Откъс от SKILL.md

Началото на файла на автора, без превод.

/perfup — Autonomous Performance Optimization

Inspired by karpathy/autoresearch: you are an autonomous performance researcher for vllm-mlx. You propose optimizations, benchmark them, keep what works, discard what doesn't, and ship a production PR.

Key Files

  • Results log: reports/perfup-results.tsv — append-only experiment log (commit, metric, status, description)
  • Optimization queue: memory/knowledge/perf_optimization_queue.md — ranked list of candidates
  • Memory index: memory/MEMORY.md — what's been done, what's known
  • Benchmark script: scripts/benchmark_engines.py
  • Model for benchmarking: Check memory for current model path. If unavailable, ask user.

The 6 Phases

Phase 1: Research

Read existing state, then discover new opportunities.

  1. Read memory/knowledge/perf_optimization_queue.md and memory/MEMORY.md
  2. If $ARGUMENTS is provided (e.g. /perfup decode), focus on that area. Otherwise broad search.
  3. Scan codebase for optimization opportunities:
    • Use Task(subagent_type=Explore) on critical paths
    • Search for TODO/FIXME/PERF/HACK comments
    • Check ml-explore/mlx-lm recent releases (gh release list --repo ml-explore/mlx-lm --limit 5)
  4. WebSearch for latest MLX inference optimizations if needed
  5. Produce candidate list, each with: problem, solution, estimated impact, effort, coverage, risk

Phase 2: Prioritize

Score and rank. Persist to memory.

  1. Score each candidate (1-5 per axis):
    • Impact: Performance gain magnitude (5 = >2x)
    • Ease: Implementation effort (5 = <1 day)
    • Coverage: Models that benefit (5 = all)
    • Safety: Regression risk (5 = zero)
  2. Sort by composite = Impact x Ease x Coverage x Safety
  3. Update memory/knowledge/perf_optimization_queue.md:
    • Completed items → "Completed" section (date + results)
    • Failed/rejected → "Rejected" section (reason)
    • Active queue → "Queue" section with [P0]-[P3] tags
  4. Present top 3 to user. Wait for confirmation before proceeding.

Phase 3: PoC Experiment Loop

This is the core loop. Inspired by autoresearch: try, measure, keep or discard. Repeat.

Целият SKILL.md в GitHub