ROCm/aiter

AI Tensor Engine for ROCm

543Stars on the repository
8Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

aiter-config-shape

01

ROCm/aiter

Skill Claude CodeCodex

How to add/upload tuned config CSVs under aiter/configs (incl. modelconfigs/) without introducing duplicate shapes, and how to find & resolve duplicate-shape collisions. Use whenever adding a model's tuned config, merging/uploading config CSVs, editing anything under aiter/configs/, or when a run hits "duplicate shape…

543 2d ago A 78 tokens original MIT

aiter-op-test

02

ROCm/aiter

Skill Claude CodeCodex

Standard structure for aiter optests under optests/test.py — @benchmark + runperftest candidate loop, a torch reference, a final markdown summary table, a main guard so the module is importable, and faithful reproduction of the real model call (output buffer, layout, shapes). Use whenever writing, rewriting, or…

543 2d ago A 103 tokens original MIT

ROCm/aiter

Skill Claude CodeCodex

Comprehensive reference for authoring FlyDSL GPU kernels on AMD GPUs. Covers the layout algebra, tiled copy/MMA, buffer ops, loop-carried range loops, SharedAllocator (LDS), autotuning, and common patterns. Use when writing, reviewing, or understanding FlyDSL kernel code.

543 2d ago C 66 tokens original MIT

ROCm/aiter

Skill Claude CodeCodex

Modernize FlyDSL kernels: replace raw MLIR dialects (arith, scf, vector, llvm, memref, math), ArithValue, redundant fx. wrapping, fx.Index, bufferops, SmemPtr/SmemAllocator, copyatomcall/mmaatomcall (loop or single atom), and raw rocdl.mfma with the current fx. surface (fx types, Python control flow, makebuffertensor…

543 2d ago A 173 tokens original MIT

ROCm/aiter

Skill Claude CodeCodex

Compile-time optimization guidance for HIP/C++ kernels using opus.hpp. Use when writing or reviewing OPUS kernels, analyzing compile time, reducing template instantiation overhead, or optimizing hipcc build performance.

543 2d ago A 46 tokens original MIT

ROCm/aiter

Skill Claude CodeCodex

Module-level JIT build-wall optimization for opus-based aiter modules. Use when an aiter JIT module's first-call build wall is a user-visible bottleneck or when adding a new module.

543 2d ago C 46 tokens original MIT

review-pr

07

ROCm/aiter

Skill Claude CodeCodex

AI code review for aiter PRs. Catches perf regressions, silent correctness bugs, dispatch gate holes, and AI-generated code patterns. Invoke with a PR number; works through fetch → semantic understanding → rule checklist → verdict. Add new rules here as patterns emerge from real reviews.

543 2d ago A 61 tokens original MIT