wenyi-li

60 mods across 1 repository, 9 stars between them.

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.

9 2mo ago A 56 tokens

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

Claude Code skill (trtllm-agent-toolkit): implement or extend TensorRT-LLM AutoDeploy fusion transforms under transform/library/ in a TensorRT-LLM checkout. Prefer existing kernels and custom ops; use Triton only when no viable existing-kernel path exists. Use ad-graph-dump for ADDUMPGRAPHSDIR workflows. Covers…

9 2mo ago A 111 tokens

flashinfer

06

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

FlashInfer — High-performance kernel library for LLM inference with optimized attention, paged KV-cache, FP8/FP4 quantization.

9 2mo ago A 30 tokens

aiter-reflection

07

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

This skill should be used when optimizing AMD GPU kernels on MI300 using the aiter project, including running op tests, benchmarking, iterating on kernel changes, and recording results in the kernel experiment database.

9 2mo ago C 46 tokens

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

Optimize inference latency and throughput of PyTorch models on AMD GPUs (MI250/MI300/MI350) with ROCm. Use when profiling and optimizing GEMM, attention, elementwise ops, torch.compile, CUDAGraphs, or Triton kernels on AMD hardware. Covers the full optimize cycle: benchmark → profile → analyze → implement → verify.…

9 2mo ago B 90 tokens

amd-rocm-porting

09

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

Port NVIDIA CUDA codebases to AMD ROCm GPUs. Use when making PyTorch models run on AMD GPUs, replacing NVIDIA-specific libraries with AMD equivalents, fixing ROCm build/runtime failures, or porting C/C++ CUDA kernels to HIP. Also covers dependency debugging and environment setup on ROCm Docker images.

9 2mo ago B 67 tokens

auto-benchmark-rocm

10

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

Run AI-driven benchmark searches on AMD ROCm with tiered server-flag sweeps for vLLM/SGLang, canonical dataset preparation, SLA or fixed-QPS benchmarking, CSV export, and resume. Adapted from SGLang auto-benchmark for MI355X (gfx950) / MI300X (gfx942) on ROCm 7.x. Use when the user wants an automated benchmark…

9 2mo ago A 117 tokens

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

Guide the agent through identifying, classifying, and restructuring warp divergence in CUDA kernels — distinguishing avoidable from unavoidable divergence, applying correct restructuring strategies, and assessing the real performance impact before spending engineering effort.

9 2mo ago A 0 tokens

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

Guide the agent through selecting the correct and efficient thread block dimensions and grid dimensions for a CUDA kernel, covering occupancy analysis, register and shared memory constraints, tail effects, persistent kernels, and when to use cudaOccupancyMaxActiveBlocksPerMultiprocessor as a decision tool.

9 2mo ago A 0 tokens

cuda-agent

15

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

You are a PyTorch and CUDA expert. Accelerate the given PyTorch Model by creating a high-performance CUDA C++ extension, targeting the best possible performance with a minimum requirement of 5% faster than torch.compile baseline.

9 2mo ago B 0 tokens

cuda-auto-tune

16

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

NCU-driven iterative optimization workflow for CUDA/CUTLASS/Triton/CuTe DSL kernels. MANDATORY: every optimization MUST start with NCU profiling, followed by multi-dimensional analysis, then targeted code modification, then re-profiling to verify. Supports roofline, memory hierarchy, warp stalls, instruction mix…

9 2mo ago C 167 tokens

cuda-c-basics

18

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

A guide to core CUDA C concepts, kernel structure, and standard programming patterns. CUDA C is used to run suitable computations on NVIDIA graphics processors.

9 2mo ago A 21 tokens

cuda-c-optimization

19

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

A set of guidance for optimizing CUDA C programs, keeping numerical results stable, and investigating bugs. CUDA C is used to run parts of programs on NVIDIA graphics processors.

9 2mo ago A 20 tokens

cuda-code-generator

21

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

Generates optimized CUDA kernel code based on performance analysis reports or algorithm type. Reads NCU analysis reports (e.g. analysis.md) and optionally existing kernel code, then produces high-quality compilable .cu files with applied optimizations. Use when the user provides an NCU analysis report or requests CUDA…

9 2mo ago A 102 tokens

cuda-kernels

22

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (getkernel) for loading…

9 2mo ago A 91 tokens

cuda-knowledge

23

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

CUDA kernel development, debugging, performance optimization, linear algebra, and multi-GPU communication for Claude Code. Use when writing, debugging, or optimizing CUDA code, GPU kernels, parallel algorithms, or CUDA library calls. Covers cuBLAS/cuBLASLt GEMM operations, CUDA Math API (half, bfloat16, FP8, FP6…

9 2mo ago A 249 tokens

cuda-optimizer

24

wenyi-li/awesome-agent-kernel-skills

Skill Claude CodeCodex

Orchestrates a full profiling-driven CUDA kernel optimization loop (write → validate → profile → analyze → optimize) until performance converges or no further gains are possible. Capabilities include generating reference implementations, writing initial kernels via cuda-code-generator, running correctness validation…

9 2mo ago A 113 tokens