VeloQ

VeloQ 收录了来自 lucifer1004 的 3 个 skills，并提供仓库级职业覆盖和站内 skill 详情页。

lucifer1004 资料在 GitHub 查看

已收集 skills

Stars

105

更新

2026-06-19

Forks

职业覆盖

软件开发工程师

1 个职业分类 · 已分类 100%

仓库浏览

这个仓库中的 skills

创作者/仓库/skill

skill

职业分类

描述

更新

ncu-profile-analysis

软件开发工程师

Analyze Nsight Compute `.ncu-rep` kernel reports using the VeloQ CLI. Use for occupancy, warp stalls, memory/instruction bottlenecks, rule findings, source/SASS/PTX correlation, and metric CSV/table export.

2026-06-19

nsys-profile-analysis

软件开发工程师

Analyze Nsight Systems `.nsys-rep` or `_pqtdir/` timeline traces using the VeloQ CLI. Use for GPU idle gaps, launch causes, CPU/GPU correlation, NVTX, CUDA graphs, metrics, sampling, and overlap/concurrency.

2026-06-19

pytorch-profile-analysis

软件开发工程师

Analyze single-file PyTorch/Kineto `.pt.trace.json(.gz)` Chrome traces using the VeloQ CLI. Use for CPU/CUDA/kernel correlation, ProfilerStep/annotation slicing, memory/shape grouping, and single-trace NCCL evidence.

2026-06-19