GitHub
benchmark-kernel
Guide for benchmarking FlashInfer kernels with CUPTI timing
☆ 4,902View skill
flashinfer-ai AI Skills
GitHub ↗Browse published AI skills maintained by flashinfer-ai. Compare skill descriptions and follow each source repository for setup instructions.
Author statistics
Indexed skills
7Repository stars across indexed skills
15,370Repository forks
2,197Average repository stars per indexed skill
2,196Repository stars may repeat across skills from the same repository.
Popular categories
Recent indexing activity
Browse skills
GitHub
debug-cuda-crash
Tutorial for debugging CUDA crashes using API logging
☆ 4,902View skill
GitHub
add-cuda-kernel
Step-by-step tutorial for adding new CUDA kernels to FlashInfer
☆ 4,902View skill
GitHub
track-models
Track popular/new open-source LLMs and update docs/model_coverage.mdx with their kernel support status. Use when discovering new models to add to the coverage tracker, checking if a specific model is covered, o...
☆ 196View skill
GitHub
clone-repos
Clone SGLang, FlashInfer repositories from GitHub to tmp/. Use when setting up the project, preparing for kernel extraction, or when the user needs the source repositories.
☆ 156View skill
GitHub
add-reference-tests
Add pytest tests to validate reference implementations in flashinfer_trace against FlashInfer or SGLang ground truth. Use when validating kernel definitions, adding tests for new op_types, or verifying referenc...
☆ 156View skill
GitHub
extract-kernel-definitions
Extract kernel schemas and definitions from SGLang model implementations with deduplication. Use when adding a new model, extracting GPU kernels (MLA, MoE, GQA, RMSNorm, GEMM), or generating Definition JSON fil...
☆ 156View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.