perfup

# /perfup — Autonomous Performance Optimization Inspired by [karpathy/autoresearch](https://github.com/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 e...