kvcache-ai / ktransformersLinks
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
☆16,188Updated this week
Alternatives and similar repositories for ktransformers
Users that are interested in ktransformers are comparing it to the libraries listed below
Sorting:
- 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…☆8,840Updated this week
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆11,896Updated 2 months ago
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.☆12,637Updated 2 months ago
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆25,718Updated 2 months ago
- GPU cluster manager for optimized AI model deployment☆4,200Updated this week
- DeepEP: an efficient expert-parallel communication library☆8,788Updated last week
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (…☆11,556Updated this week
- ☆4,569Updated 6 months ago
- Integrate the DeepSeek API into popular softwares☆34,642Updated 2 months ago
- MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone☆22,330Updated 2 months ago
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,937Updated 6 months ago
- GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型☆6,947Updated 5 months ago
- Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.☆49,366Updated this week
- SGLang is a fast serving framework for large language models and vision language models.☆21,166Updated this week
- Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆16,985Updated 2 weeks ago
- Easily build AI systems with Evals, RAG, Agents, fine-tuning, synthetic data, and more.☆4,462Updated this week
- A modular graph-based Retrieval-Augmented Generation (RAG) system☆29,701Updated last week
- Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model☆8,030Updated 10 months ago
- Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and pe…☆3,846Updated 6 months ago
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,377Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆5,944Updated this week
- A simple screen parsing tool towards pure vision based GUI agent☆23,968Updated 3 months ago
- Retrieval and Retrieval-augmented LLMs☆11,004Updated last month
- MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks☆8,453Updated 2 months ago
- Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.☆7,222Updated 3 weeks ago
- No fortress, purely open ground. OpenManus is Coming.☆51,194Updated 3 weeks ago
- 🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation☆18,431Updated 2 weeks ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,399Updated 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!☆35,517Updated this week
- 🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!☆5,588Updated last week