deepseek-ai / FlashMLALinks
FlashMLA: Efficient Multi-head Latent Attention Kernels
☆12,456Updated this week
Alternatives and similar repositories for FlashMLA
Users that are interested in FlashMLA are comparing it to the libraries listed below
Sorting:
- DeepEP: an efficient expert-parallel communication library☆8,967Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆6,162Updated last week
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆2,919Updated 3 weeks ago
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,964Updated 8 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,701Updated this week
- A high-performance distributed file system designed to address the challenges of AI training and inference workloads.☆9,706Updated this week
- Expert Parallelism Load Balancer☆1,344Updated 10 months ago
- Analyze computation-communication overlap in V3/R1.☆1,141Updated 10 months ago
- FlashInfer: Kernel Library for LLM Serving☆4,935Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆5,094Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆6,052Updated this week
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,995Updated last year
- A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations☆16,458Updated this week
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,891Updated 2 years ago
- DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding☆5,214Updated 11 months ago
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.☆3,509Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆23,439Updated this week
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆3,328Updated 7 months ago
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,044Updated 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…☆3,914Updated 7 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆18,963Updated this week
- Fully open reproduction of DeepSeek-R1☆25,866Updated 2 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆8,949Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,576Updated this week
- Simple RL training for reasoning☆3,830Updated last month
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.☆13,234Updated last week
- s1: Simple test-time scaling☆6,636Updated 7 months ago
- Democratizing Reinforcement Learning for LLMs☆5,081Updated this week
- A lightweight data processing framework built on DuckDB and 3FS.☆4,920Updated 11 months ago
- Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆18,178Updated last week