deepseek-ai / open-infra-indexLinks
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
☆7,914Updated 4 months ago
Alternatives and similar repositories for open-infra-index
Users that are interested in open-infra-index are comparing it to the libraries listed below
Sorting:
- DeepEP: an efficient expert-parallel communication library☆8,513Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆5,715Updated last week
- FlashMLA: Efficient MLA kernels☆11,721Updated 3 weeks ago
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.☆2,858Updated 6 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆3,967Updated this week
- A high-performance distributed file system designed to address the challenges of AI training and inference workloads.☆9,303Updated last week
- A Datacenter Scale Distributed Inference Serving Framework☆4,997Updated this week
- Expert Parallelism Load Balancer☆1,265Updated 5 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆18,021Updated this week
- Analyze computation-communication overlap in V3/R1.☆1,097Updated 5 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆13,293Updated this week
- FlashInfer: Kernel Library for LLM Serving☆3,723Updated last week
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆3,142Updated 2 months ago
- A lightweight data processing framework built on DuckDB and 3FS.☆4,776Updated 6 months ago
- A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations☆15,040Updated last week
- Nano vLLM☆6,553Updated 2 weeks ago
- My learning notes/codes for ML SYS.☆3,632Updated this week
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,939Updated 11 months ago
- Democratizing Reinforcement Learning for LLMs☆4,177Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,605Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,039Updated last week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆1,900Updated 5 months ago
- ☆1,582Updated 9 months ago
- DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding☆5,045Updated 6 months ago
- Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆12,483Updated 4 months ago
- Supercharge Your LLM with the Fastest KV Cache Layer☆5,210Updated this week
- Fully open reproduction of DeepSeek-R1☆25,436Updated last week
- Simple RL training for reasoning☆3,745Updated last month
- 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…☆3,618Updated 3 months ago
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆4,518Updated last month