菜单
Parent overview skill for ROCm Data Science (ROCm-DS) components and SMI tools. Provides guidance on routing workloads, compatibility triage, and component-specific tasks like hipDF, hipVS, and hipMM.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Develop and extend gfxGRAPH internals — add gap bridges, fix HIP/ROCm issues, debug graph capture failures, and understand the architecture. Covers BridgedCUDAGraph, ShapeBucketPool, ConditionalGraph, native bridge, and the monkey-patch system. USE FOR: extend gfxGRAPH, add new gap bridge, fix gfxGRAPH bug, understand gfxGRAPH architecture, modify BridgedCUDAGraph, add gfxGRAPH feature, debug graph capture internals, improve gfxGRAPH performance, gfxGRAPH C++ native bridge, write gfxGRAPH tests. DO NOT USE FOR: just using gfxGRAPH in a project (use gfxgraph-integration), general ROCm issues.
Benchmark gfxGRAPH internals, run the public benchmark suite, and compare performance between Python and Rust.
Guide and resources for deployment and development using the ROCm/AMD ATOM (AiTer Optimized Model) inference backend.
Validates and benchmarks ROCm-DS component ports against their CPU baselines (e.g., pandas vs hipDF). Use this to generate parity tests, verify correctness, and measure the performance speedups of GPU-accelerated code.
Verifies whether a requested ROCm-DS workflow is officially supported, source-build feasible, or experimental on the target system.
Migrates pandas-like workflows to hipDF and cudf.pandas style acceleration, auditing for unsupported features.
| name | rocm-ds-smi-science-tools |
| description | Parent overview skill for ROCm Data Science (ROCm-DS) components and SMI tools. Provides guidance on routing workloads, compatibility triage, and component-specific tasks like hipDF, hipVS, and hipMM. |
This is the parent skill for managing tasks related to ROCm Data Science (ROCm-DS) and AMD GPU-accelerated scientific computing tools.
Use this skill to determine the appropriate nested skill to invoke when working with ROCm-DS components, porting data science workflows to ROCm, or handling installation and compatibility.
compatibility-triage: Verifies whether a requested ROCm-DS workflow is officially supported, source-build feasible, or experimental on the target system.hipdf-pandas-port: Migrates pandas-like workflows to hipDF and cudf.pandas style acceleration, auditing for unsupported features.hipgraph-analytics: Leverages GPU acceleration to process and analyze complex graph structures using hipGRAPH.hipmm-memory-ops: Utilizes the HIP Memory Manager (hipMM) for advanced GPU memory pooling, efficient allocation, and data movement.hipraft-primitives: Utilizes hipRAFT for foundational, reusable GPU-accelerated primitives like clustering, dimensionality reduction, and statistical operations.hipvs-ann: Selects, builds, benchmarks, and validates hipVS ANN indexes and query paths for ROCm-DS workloads.install-build: Handles installation and source compilation of ROCm-DS components via conda, PyPI, or source builds.pipeline-integration: Integrates ROCm-DS components into broader data science pipelines.benchmark-validate: Validates and benchmarks ROCm-DS component ports against their CPU baselines (e.g., pandas vs hipDF).tool-router: Classifies and routes tasks to the appropriate ROCm-DS component (hipDF, hipVS, hipGRAPH, hipRAFT, hipMM) based on workload requirements.