A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
☆16,804Mar 18, 2026Updated this week
Alternatives and similar repositories for ktransformers
Users that are interested in ktransformers are comparing it to the libraries listed below
Sorting:
- SGLang is a high-performance serving framework for large language models and multimodal models.☆24,829Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆73,479Updated this week
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆12,521Feb 6, 2026Updated last month
- Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.☆54,096Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,953Updated this week
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆68,728Updated this week
- FlashInfer: Kernel Library for LLM Serving☆5,194Updated this week
- Production-ready platform for agentic workflow development.☆133,787Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,694Mar 13, 2026Updated last week
- RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to creat…☆75,590Updated this week
- DeepEP: an efficient expert-parallel communication library☆9,053Feb 9, 2026Updated last month
- No fortress, purely open ground. OpenManus is Coming.☆55,377Feb 11, 2026Updated last month
- LLM inference in C/C++☆98,911Updated this week
- Fast and memory-efficient exact attention☆22,832Updated this week
- 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-p…☆9,134Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆6,268Feb 27, 2026Updated 3 weeks ago
- Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.☆56,760Updated this week
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆13,120Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆41,869Updated this week
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,972May 15, 2025Updated 10 months ago
- A modular graph-based Retrieval-Augmented Generation (RAG) system☆31,670Updated this week
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆26,969Jan 9, 2026Updated 2 months ago
- Fully open reproduction of DeepSeek-R1☆25,953Nov 24, 2025Updated 3 months ago
- A simple screen parsing tool towards pure vision based GUI agent☆24,546Sep 12, 2025Updated 6 months ago
- Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.☆165,557Updated this week
- High-speed Large Language Model Serving for Local Deployment☆8,834Jan 24, 2026Updated last month
- A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Multimodal Live Streaming on Your Phone☆24,144Mar 7, 2026Updated 2 weeks ago
- Performance-optimized AI inference on your GPUs. Unlock superior throughput by selecting and tuning engines like vLLM or SGLang.☆4,653Updated this week
- Making large AI models cheaper, faster and more accessible☆41,362Updated this week
- 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…☆4,173Updated this week
- 🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!☆41,885Feb 6, 2026Updated last month
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,958Updated this week
- AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs☆41,634Updated this week
- User-friendly AI Interface (Supports Ollama, OpenAI API, ...)☆127,399Mar 16, 2026Updated last week
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.☆15,704Mar 4, 2026Updated 2 weeks ago
- ☆91,959Jun 27, 2025Updated 8 months ago
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆39,428Jun 2, 2025Updated 9 months ago
- 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…☆37,581Nov 10, 2025Updated 4 months ago
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, …☆13,263Updated this week