このプロンプトをコピーして、使用中の AI アシスタントに送ってください。
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/ROCm/ATOM.リポジトリの README を読み込んでいます…
収集済み skill 6 件中 6 件を表示しています。
Review an ATOM PR to the maintainer's bar and draft the review for posting. Combines the team rule catalog (silent bypass, coverage gaps, hardcoded arch/dtype, uninitialized state, cross-repo aiter/plugin sync, backbone risk, perf evidence, AI-generated code…
原文の言語: 英語
Coding patterns and architecture index for the ATOM LLM inference engine
原文の言語: 英語
Capture a PyTorch profiler / kineto trace from a running ATOM server for a short benchmark window. Use when the user asks for "a trace", "profiler trace", "GPU trace", or "抓 trace" for performance investigation — what kernels ran, what's on the critical path,…
原文の言語: 英語
Run any ATOM workload — accuracy eval (GSM8K via lm_eval), performance benchmark, concurrency sweep, offline simple_inference, or fault repro under rocm-debug-agent. Use when the user asks to "test accuracy", "测精度", "跑 GSM8K", "跑 benchmark", "test…
原文の言語: 英語
Identify which GPU kernel is faulting/hanging in ATOM via rocm-debug-agent (for faults/asserts) or rocgdb (for silent livelocks). debug-agent dumps wave registers + faulting PC + (with --save-code-objects) disassembled code object on memory faults /…
原文の言語: 英語
Locate forward numerical bugs by dumping intermediate tensors from a target implementation and a known-good reference, then bisecting layer by layer. Also covers batch-invariance bisect (the same token at any batch position should produce a bitwise-identical…
原文の言語: 英語
README を読み込めませんでした。リポジトリの Skill 一覧は下で引き続き確認できます。