Krish Gupta
Community@krxgu · Mumbai
27Followers
|36Public Repos
|7Published Skills
21 | GSoC'26 @llvm , GSoC'25 @gnuradio | Inference & Compilers.
Agent Skills by Krish Gupta
Showing 7 vetted skills indexed across 1 GitHub repositories.
KrxGu54
Write a Numerically Stable Kernel
Identify and mitigate numerical instability in GPU compute kernels with dtype-annotated stabilizations.
Community
Advanced
KrxGu54
Write CUDA Reduction Kernel
Design CUDA reduction kernels with warp and block reductions.
Community
Advanced
KrxGu54
Write CUDA Softmax Kernel
Implement numerically stable CUDA softmax kernels with fp32 accumulation and masking.
Community
Advanced
KrxGu54
Write CUDA GEMM Kernel
Design and implement a CUDA GEMM kernel with FP32 accumulation and tiling.
Community
Advanced
KrxGu54
Write a Triton Softmax Kernel
Implement a numerically stable Triton softmax kernel with fp32 accumulation and multi-block online rescaling.
Community
Advanced
KrxGu54
Write an INT8 Quantized Kernel
Design INT8 quantized GEMM kernels with dp4a and INT32 accumulation for NVIDIA GPUs.
Community
Advanced
KrxGu54
Write a Backend-Agnostic Kernel Plan
Plan backend-agnostic compute kernels for NVIDIA, AMD, and CPU targets.
Community
Advanced