guocuimi

chatbot-ui

AI chat for every model.

triton

Development repository for the Triton language and compiler

mamba

Mamba SSM architecture

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Yi

A series of large language models trained from scratch by developers @01-ai

LookaheadDecoding

flashinfer

FlashInfer: Kernel Library for LLM Serving

Jinja2Cpp

Jinja2 C++ (and for C++) almost full-conformance template engine implementation

nvbench

CUDA Kernel Benchmarking Library

ByteTransformer

optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052

hal-9100

Edge full-stack LLM platform. Written in Rust

calm

CUDA/Metal accelerated language model inference

pyglove

Manipulating Python Programs

ScaleLLM

A high-performance inference system for large language models, designed for production environments.

run-clang-format

A wrapper script around clang-format, suitable for linting multiple files and to use for continuous integration

cuda_hgemm

Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruction.

MatmulTutorial

A Easy-to-understand TensorOp Matmul Tutorial

sirius

A Plonkish folding framework for Incrementally Verifiable Computation (IVC).

langfun

Empower LLMs with Symbols.

cute-gemm

SA-Segment-Anything

Vision-oriented multimodal AI

LLMBench

A library for validating and benchmarking LLMs inference.