PyTorch · Performance optimization

Measures and shrinks the ExecuTorch runtime binary by building a size test, analyzing it with bloaty and landing each reduction as its own pull request.

pytorch/executorch

Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.

stas00/the-art-of-debugging

Profiles, benchmarks and tunes AI training workloads on Moore Threads MUSA GPUs with a measurement-first process that keeps model behavior unchanged.

open-infra-skills/infra-skills

Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.

graphsignal/graphsignal

Inspect a PyTorch baseline with torch.compile graphs/code and torch.profiler before drafting a custom kernel, then compare TileLang and PyTorch timelines, forward/backward regions, and allocations.

sablin39/tilelang-cuda-skills

Detects CPU, GPU, memory and disk resources before heavy scientific tasks and writes a JSON file with advice on parallelism, out-of-core work and GPU use.

davila7/claude-code-templates

End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torchnpu PyTorch custom op) project.

ascend-ai-coding/awesome-ascend-skills

Profile ExecuTorch model execution. Use when measuring performance, analyzing operator timing, or debugging slow models.

pytorch/executorch

Benchmarks LLM inference and drives GPU kernel optimization with Magpie.

amd/skills

Optimize or review eager CPU-only Albucore PyTorch runtime paths with benchmark-backed decisions.

albumentations-team/albucore

Orchestrates modular PyTorch profiler trace analysis with TraceLens: generates perf reports, prepares category data, runs system-level and compute-kernel subagents in parallel, validates outputs…

amd/skills

优化实际模型推理链路，将正确性对齐、分段 profiling、显存与数据搬运、TensorRT/ONNX/PyTorch 后端、attention/kernel、FP8/compile、缓存与少步采样、质量回归、GPU 成本和服务验收串成同一实验闭环。当用户要求推理提速、降低显存或 GPU 成本、复现模型效果、定位 GPU 利用率低、优化图像/视频/扩散模型或自托管 LLM 时使用，提供…

majiayu000/spellbook

面向 Ascend PyTorch Profiler / msprof DB（如 ascendpytorchprofiler.db、msprof.db）的 SQL 分析技能。将自然语言问题（算子耗时、通信、下发、调度、schema/table 查询）转为安全可执行 SQL，并按需从官方文档提取表结构详情。

ascend-ai-coding/awesome-ascend-skills