A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
☆18,731Jul 20, 2026Updated this week
Alternatives and similar repositories for ktransformers
Users that are interested in ktransformers are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- SGLang is a high-performance serving framework for large language models and multimodal models.☆30,545Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆86,727Updated this week
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆12,755Apr 30, 2026Updated 2 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆5,925Updated this week
- Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.☆68,541Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- FlashInfer: Kernel Library for LLM Serving☆5,988Updated this week
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆73,397Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,965Updated this week
- Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self…☆149,503Updated this week
- DeepEP: an efficient expert-parallel communication library☆9,862Jul 14, 2026Updated last week
- No fortress, purely open ground. OpenManus is Coming.☆57,495Feb 11, 2026Updated 5 months ago
- Fast and memory-efficient exact attention☆24,497Updated this week
- LLM inference in C/C++☆121,053Updated this week
- RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to creat…☆85,463Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 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…☆9,440Updated this week
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆7,534Updated 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…☆14,162Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆42,752Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆6,674Updated this week
- A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.☆5,351Updated this week
- Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.☆75,212Updated this week
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆8,026May 15, 2025Updated last year
- A modular graph-based Retrieval-Augmented Generation (RAG) system☆34,533Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆27,407Jan 9, 2026Updated 6 months ago
- A simple screen parsing tool towards pure vision based GUI agent☆25,179Updated this week
- Fully open reproduction of DeepSeek-R1☆26,411Apr 2, 2026Updated 3 months ago
- Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.☆176,510Updated this week
- High-speed Large Language Model Serving for Local Deployment☆9,665May 11, 2026Updated 2 months ago
- Making large AI models cheaper, faster and more accessible☆41,419Jul 13, 2026Updated last week
- A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone☆25,948Jun 25, 2026Updated 3 weeks 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…☆4,854Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,571Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,183Updated this week
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.☆16,821Mar 4, 2026Updated 4 months ago
- ☆91,990Jun 27, 2025Updated last year
- 🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!☆53,654Jun 28, 2026Updated 3 weeks ago
- Nano vLLM☆14,557Apr 26, 2026Updated 2 months ago
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆39,494May 1, 2026Updated 2 months ago
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL…☆14,866Updated this week