Skip to content
View airlsyn's full-sized avatar

Block or report airlsyn

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
10 results for source starred repositories written in Cuda
Clear filter

DeepEP: an efficient expert-parallel communication library

Cuda 8,694 972 Updated Nov 5, 2025

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Cuda 5,861 736 Updated Oct 15, 2025

Fast parallel CTC.

Cuda 4,073 1,036 Updated Mar 4, 2024

FlashInfer: Kernel Library for LLM Serving

Cuda 4,018 558 Updated Nov 6, 2025

Tile primitives for speedy kernels

Cuda 2,868 192 Updated Nov 4, 2025

NCCL Tests

Cuda 1,325 326 Updated Nov 3, 2025

FSA/FST algorithms, differentiable, with PyTorch compatibility.

Cuda 1,276 230 Updated Nov 4, 2025

An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).

Cuda 270 22 Updated Jul 16, 2025

PyTorch bindings for CUTLASS grouped GEMM.

Cuda 126 77 Updated May 29, 2025

An example project showing how to build a pip-installable Python package that invokes custom CUDA/C++ code

Cuda 14 2 Updated Jul 12, 2017