Debug Quantized Kernel Accuracy
A Claude skill from tensormux/kernel-skills.
Write Triton Rmsnorm Kernel
A Claude skill from tensormux/kernel-skills.
Write Triton Attention Kernel
A Claude skill from tensormux/kernel-skills.
Choose Launch Configuration
A Claude skill from tensormux/kernel-skills.
Write Triton Kv Cache Append Kernel
A Claude skill from tensormux/kernel-skills.
Write Triton Rope Kernel
A Claude skill from tensormux/kernel-skills.
Write Vllm Custom Op Integration Plan
A Claude skill from tensormux/kernel-skills.
Write Cuda Reduction Kernel
A Claude skill from tensormux/kernel-skills.
Fuse Elementwise Ops
A Claude skill from tensormux/kernel-skills.
Write Triton Dequant Kernel
A Claude skill from tensormux/kernel-skills.
Avoid Warp Divergence
A Claude skill from tensormux/kernel-skills.
Write Cuda Softmax Kernel
A Claude skill from tensormux/kernel-skills.
Port Cuda Kernel To Hip
A Claude skill from tensormux/kernel-skills.
Debug Cuda Kernel Correctness
A Claude skill from tensormux/kernel-skills.
Handle Boundary Conditions
A Claude skill from tensormux/kernel-skills.
Write Numerically Stable Kernel
A Claude skill from tensormux/kernel-skills.
Optimize Prefill Vs Decode Kernels
A Claude skill from tensormux/kernel-skills.
Optimize Triton Block Parameters
A Claude skill from tensormux/kernel-skills.
Write Triton Fused Add Rmsnorm Kernel
A Claude skill from tensormux/kernel-skills.
Optimize Global Memory Access
A Claude skill from tensormux/kernel-skills.
Write Cuda Gemm Kernel
A Claude skill from tensormux/kernel-skills.
Write Triton Softmax Kernel
A Claude skill from tensormux/kernel-skills.
Write Int8 Quantized Kernel
A Claude skill from tensormux/kernel-skills.
Write Triton Sampling Kernel
A Claude skill from tensormux/kernel-skills.
Write Triton Silu Mul Kernel
A Claude skill from tensormux/kernel-skills.
Port Cuda Kernel To Triton
A Claude skill from tensormux/kernel-skills.
Optimize Shared Memory Tiling
A Claude skill from tensormux/kernel-skills.
Write Backend Agnostic Kernel Plan
A Claude skill from tensormux/kernel-skills.
Write Cuda Layernorm Kernel
A Claude skill from tensormux/kernel-skills.
Choose Tile Size And Work Partitioning
A Claude skill from tensormux/kernel-skills.
Write Triton Layernorm Kernel
A Claude skill from tensormux/kernel-skills.
Write Tensorrt Plugin Integration Plan
A Claude skill from tensormux/kernel-skills.
Write Kernel Test Plan
A Claude skill from tensormux/kernel-skills.
Write Fp8 Kernel
A Claude skill from tensormux/kernel-skills.
Write Triton Gemm Kernel
A Claude skill from tensormux/kernel-skills.