whutbd

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

learntorch

Tutorials for PyTorch C++

Leetcode

Play Leetcode with different programming language

cuda_code

easy cuda code

kimi-free-api

🚀 KIMI AI 长文本大模型逆向API白嫖测试【特长：长文本解读整理】，支持高速流式输出、智能体对话、联网搜索、长文档解读、图像OCR、多轮对话，零配置部署，多路token支持，自动清理会话痕迹。

ngram

The n-gram Language Model

llama2.cpp

Inference Llama 2 in one file of pure C++

FastDeploy

⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models with end-to-end optimization, multi-platform and multi-framework support.

TensorRT_Tutorial

cute-gemm

tensorrtllm_backend

The Triton TensorRT-LLM Backend

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

riven

CPU Memory Compiler and Parallel programing

MegRay

A communication library for deep learning

cuda_sgemm

ChatGLM-6B

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

InferLLM

a lightweight LLM model inference framework

tensorrt-cpp-api

TensorRT C++ API Tutorial

Play-Leetcode

My Solutions to Leetcode problems. All solutions support C++ language, some support Java and Python. Multiple solutions will be given by most problems. Enjoy:) 我的Leetcode解答。所有的问题都支持C++语言，一部分问题支持Java语言。近乎所有问题都会提供多个算法解决。大家加油！：）

flash-attention-minimal

Flash Attention in ~100 lines of CUDA (forward pass only)

KuiperLLama

动手实现大模型推理框架

cudnn-frontend

cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it

Kolors

Kolors Team

fish-speech

Brand new TTS solution

stable-ts

Timestamping Spoken Words

llumnix

Efficient and easy multi-instance LLM serving

knowhere

Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

MedicalGPT

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。