xorbitsai / inferenceLinks
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.
☆8,867Updated this week
Alternatives and similar repositories for inference
Users that are interested in inference are comparing it to the libraries listed below
Sorting:
- GPU cluster manager for optimized AI model deployment☆4,254Updated this week
- Retrieval and Retrieval-augmented LLMs☆11,027Updated this week
- GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型☆6,968Updated 5 months ago
- Question and Answer based on Anything.☆13,792Updated 8 months ago
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,407Updated this week
- MS-Agent: Lightweight Framework for Empowering Agents with Autonomous Exploration in Complex Task Scenarios☆3,699Updated this week
- AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents☆17,799Updated last week
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.☆12,694Updated 2 months ago
- fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tp…☆4,113Updated 2 weeks ago
- A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations☆16,222Updated this week
- 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…☆36,807Updated last month
- FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data process…☆26,627Updated this week
- 🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。☆19,580Updated this week
- 分享一些好用的 Dify DSL 工作流程，自用、学习两相宜。 Sharing some Dify workflows.☆9,759Updated 6 months ago
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (…☆11,695Updated this week
- RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to creat…☆69,929Updated this week
- C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)☆2,969Updated last year
- ChatOllama is an open-source AI chatbot that brings cutting-edge language models to your fingertips while keeping your data private and s…☆3,440Updated last month
- Netease Youdao's open-source embedding and reranker models for RAG products.☆1,851Updated 3 months ago
- ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型☆13,739Updated 11 months ago
- BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI…☆10,628Updated this week
- Openai style api for open large language models, using LLMs just as chatgpt! Support for LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, X…☆2,461Updated last year
- MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks☆8,467Updated 2 months ago
- OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, …☆6,441Updated this week
- The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.☆19,953Updated 3 weeks ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆65,334Updated this week
- Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、…☆6,616Updated last year
- Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.☆7,244Updated last month
- A series of large language models developed by Baichuan Intelligent Technology☆4,123Updated last year
- A Next-Generation Training Engine Built for Ultra-Large MoE Models☆5,024Updated last week