#
8000
Starred repositories
LiveBench: A Challenging, Contamination-Free LLM Benchmark
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Llava, GLM4…
A streamlined and customizable framework for efficient large model evaluation and performance benchmarking
Production-ready platform for agentic workflow 10000 development.
Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with …
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorR…
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
Summary of the Specs of Commonly Used GPUs for Training and Inference of LLM
No fortress, purely open ground. OpenManus is Coming.
FlashInfer: Kernel Library for LLM Serving
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
《赋范大模型技术社区》是针对各阶大模型学习者量身打造的基于各类大模型，包括环境设置、本地部署、高效微调、开发实战等技能在内的全流程指导！
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
A Framework of Small-scale Large Multimodal Models
A Simple Framework of Small-scale LMMs for Video Understanding
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06
Question and Answer based on Anything.
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
This repository will consist of advanced RAG applications.
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
A high-throughput and memory-efficient inference and serving engine for LLMs
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering