Ma-Dan

Llama2-CoreML

Llama2 for iOS implemented using CoreML.

llama.cpp

Port of Facebook's LLaMA model in C/C++

BasicCUDA

ChatGLM-MNN

Pure C++, Easy Deploy ChatGLM-6B.

DAIL-SQL

A efficient and effective few-shot NL2SQL method on GPT-4.

DB-GPT

Revolutionizing Database Interactions with Private LLM Technology

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

FastChat

The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

fastllm

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

Fooocus

Focus on prompting and generating

icefall

InferLLM

a lightweight LLM model inference framework

k2

FSA/FST algorithms, differentiable, with PyTorch compatibility.

linorobot2

Autonomous mobile robots (2WD, 4WD, Mecanum Drive)

llama

Inference code for LLaMA models

llama2.c

Inference Llama 2 in one file of pure C

LLaSM

第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验，同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。

MatmulTutorial

A Easy-to-understand TensorOp Matmul Tutorial

PythonRobotics

Python sample codes for robotics algorithms.

RTK

Reconstruction Toolkit

RWKV-LM

RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

sherpa

Speech-to-text server framework with next-gen Kaldi

sherpa-ncnn

Real-time speech recognition using next-gen Kaldi with ncnn

TIGRE

TIGRE: Tomographic Iterative GPU-based Reconstruction Toolbox

TNN

TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and per

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit

WeTextProcessing

Text Normalization & Inverse Text Normalization

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

Zhongjing

A Chinese medical ChatGPT based on LLaMa, training from large-scale pretrain corpus and multi-turn dialogue dataset.