zzxxxl

langchain

🦜🔗 Build context-aware reasoning applications

dify

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

llama_index

LlamaIndex is a data framework for your LLM applications

Langchain-Chatchat

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

LocalAI

:robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. Features: Generate Text, Audio, Video, Images, Voice Cloning, Distributed inference

ragflow

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

ceph

Ceph is a distributed object, block, and file storage platform

wandb

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

einops

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

mergekit

Tools for merging pretrained large language models.

trader

交易模块

MobileAgent

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

lectures

Material for cuda-mode lectures

kernl

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

evolutionary-model-merge

Official repository of Evolutionary Optimization of Model Merging Recipes

CUDA-Learn-Notes

🎉 CUDA Learn Notes with PyTorch: fp32、fp16/bf16、fp8/int8、flash_attn、sgemm、sgemv、warp/block reduce、dot prod、elementwise、softmax、layernorm、rmsnorm、hist etc.

DiskANN

Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search

gpt-assistant-android

免费的ChatGPT API的安卓语音助手，可用音量键唤起并进行语音交流，支持联网、Vision拍照识图、提问模板等功能 | A free ChatGPT API voice assistant for Android, activated via volume keys for voice interaction, supporting features such as network connectivity, Vision photo recognition, and question templates.

flash-attention-minimal

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

DB-GPT

An LLM Based Diagnosis System (https://arxiv.org/pdf/2312.01454.pdf)

DistServe

Disaggregated serving system for Large Language Models (LLMs).

astra-sim

ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale

vidur

A large-scale simulation framework for LLM inference

refusal_direction

Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".

LLM-Extrapolation

Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"

lottery-ticket-adaptation

Lottery Ticket Adaptation

Evaluation-Multimodal-LLMs-Survey

A Survey on Benchmarks of Multimodal Large Language Models

RepresentationSurgery

Representation Surgery for Multi-Task Model Merging. ICML, 2024.

Proteus