// Run and interpret hipfire GPU diagnostics for ROCm/HIP bring-up, missing kernels, test_kernels 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.
| name | hipfire-diag |
| description | Run and interpret hipfire GPU diagnostics for ROCm/HIP bring-up, missing kernels, test_kernels 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 this skill for read-only diagnosis of a hipfire checkout or installed runtime. It gathers GPU, ROCm, kernel-blob, build, and optional inference-test signals, then maps failures to concrete next steps.
.agents/skills/hipfire-diag/run-diagnostics.sh [MODEL_PATH]
interpret.md for failure mapping and fix-suggestions.md for
platform-specific remediation../scripts/coherence-gate-dflash.sh before claiming correctness.Cleanly stop, free the port, and restart `hipfire serve`. Use when serve "Failed to start (port in use)", a stale daemon holds VRAM, an os-error-2/JSON-parse pre-warm crash left a zombie singleton, or you just want a guaranteed-fresh daemon. Kills both bun CLI serve and the spawned target/release/examples/daemon, reaps stale ~/.hipfire/daemon.pid + serve.pid + GPU lock, fuser-frees the port, then relaunches.
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 through Atlas for AR/DFlash perf validation.
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 dispatch.rs's arch-conditional branches. Captures the WMMA operand-shape matrix, builtin name table per arch, dispatch routing convention, validation procedure (channel-test / coherence-gate / speed-gate), contributor onboarding workflow, and known correctness traps. Triggers on phrases like "port to gfx12", "9070 XT support", "R9700 support", "WMMA gfx12", "Cannot select intrinsic wmma", "amdgcn.wmma", "new arch port", "cross-arch kernel".
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 hipfire serve/run flow.
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 wants an agent-readable "left on table" summary from Atlas rows.
Optimize hipfire HIP/compute kernels — pick a tuning lever (multi-row, K-tile depth, prefetch, wave-size port, WMMA/MFMA, fused projections, ISA flags) and validate the win across the supported RDNA arch matrix. Use when you've identified a hot kernel, want to land a real perf win, and need to NOT regress on archs you don't have hardware for. Codifies the methodology from this repo's actual perf history — wave64 CDNA3 port (commit 4105035, 2× decode), nontemporal-load revert (34eb024, -13% caught only by clean-baseline bisect), gfx12 WMMA port (PR