Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

JAX backend for SGL

A alibaba canal client for golang

SGLang is a high-performance serving framework for large language models and multimodal models.

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

FlashMLA: Efficient Multi-head Latent Attention Kernels

DeepEP: an efficient expert-parallel communication library

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

CUDA on non-NVIDIA GPUs

A tool to modify ONNX models in a visualization fashion, based on Netron and Flask.

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

pkg download & installation directly on Vita

GLake: optimizing GPU memory management and IO transmission.

An Advanced Launcher for miHoYo/HoYoverse Games

Source code for the X Recommendation Algorithm

An unofficial cuda assembler, for all generations of SASS, hopefully ：）

Acceleration with Simd inTrinsic, Easy and Reusable

Implementations of SIMD instruction sets for systems which don't natively support them.

Autograder Web UI

A primitive library for neural network

This is a demo how to write a high performance convolution run on apple silicon