Scan open pull requests and reconcile the needs-review label. Use before running agentic-pr-static-review to find PRs needing a review pass. Outputs JSON with reviewed, needsreview, labelled, clean, incomplete, and error arrays.
Run bounded toolless inference on a review capsule and produce a review proposal with hardware validation triage. Use when a review capsule has been built and needs inference, or to run the full inspect pipeline (build → infer) on a PR. Outputs a structured ReviewProposal with triage data for downstream agent…
Use for hipfire quant calibration, imatrix-driven experiments, KLD/PPL quality evaluation, k-map/format selection, MQ/HFQ/HFP/MFP tradeoff work, ParoQuant-style weight transform planning, and KV policy planning. Use when deciding whether a calibrated model candidate should be promoted, rejected, packaged, or sent…
Port hipfire compute kernels to a new RDNA / CDNA architecture (gfx1201/gfx1200/gfx94x/gfx1150/etc.). Use when adding support for a new GPU arch, fixing arch-specific kernel codegen failures (e.g. "Cannot select intrinsic %llvm.amdgcn.wmma..."), or refactoring rdna-compute arch-conditional dispatch. Captures the…
Triage and repair hipfire runtime failures such as daemon hangs, stale serve.pid, port 11435 conflicts, ROCm include-path problems, missing precompiled kernels, VRAM OOM, kernel JIT failures, and multi-turn recall regressions. Use after diagnostics identify a likely runtime issue or when the user asks to fix a broken…
Run and interpret hipfire GPU diagnostics for ROCm/HIP bring-up, missing kernels, testkernels failures, inference smoke failures, and install/runtime environment problems. Use when a user asks to diagnose hipfire, check GPU readiness, run baseline tests, or explain diagnostic output.
Use Kernel Atlas to collect phase-aware hipfire measurements and render ISA Fit View visualizations for AMD GPU kernels, quant formats, and architectures. Use when a user asks how MQ/HFQ/HFP/Q8 quants occupy hardware, asks for an ASCII ISA visualization, wants to compare gfx1010/gfx1030/gfx11/gfx12 kernel fit, or…
Optimize hipfire HIP/compute kernels — pick one tuning lever (multi-row, K-tile depth, prefetch, wave-size port, WMMA/MFMA, fused projections, ISA flags) and validate it with profile → ISA → fresh-process measurement. Use when a hot kernel is identified, you want a real perf win, and you must not regress adjacent…
Guide a tester through hipfire bring-up, serve smoke, claim-scoped harnesses, and benchmark reporting on AMD RDNA/CDNA GPUs. Use when the user wants a route-oriented test plan or an upstream-ready tester report. Retired batteries are not current evidence — use docs/VALIDATION.md.
Use when porting a hipfire feature/fix branch authored against pre-0.1.20 master onto post-modular master. Walks through the engine→hipfire-runtime + per-arch-crate split mechanically, then surfaces semantic conflicts that need human judgment.
Discovery hook for retained AQL/PM4 (Redline) work. Use when admitting a model to retained replay, changing recorder/tape/PM4/queue policy, model reset or fallback, kernels on a retained route, or making a Redline-attributed bench claim. Routes to docs/REDLINE.md and docs/VALIDATION.md — does not fork procedure.
AGENTS.md instructions for warpfront/hipfire, covering agents.md — project notice + testing playbook, notice for ai agents working with hipfire, what hipfire is, what this notice asks of you and what this notice does not ask of you.
Claude Code instructions for warpfront/hipfire, covering hipfire: rust-native inference engine for amd rdna gpus, mission, architecture, pflash status and building, testing & gates.