XPU-Forces/mojo_opset

High-performance LLM operator library built on TileLang.

DeepGEMM: clean and efficient BLAS kernel library on GPU

A kernel library written in tilelang

High Performance LLM Inference Operator Library

Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

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

Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.

Accessible large language models via k-bit quantization for PyTorch.

Tutel MoE: Optimized Mixture-of-Experts Library, Support GLM/Kimi/Gpt/DeepSeek/Qwen using FP8/NVFP4/MXFP4