deepseek-ai / FlashMLALinks
FlashMLA: Efficient Multi-head Latent Attention Kernels
☆11,913Updated 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☆8,808Updated last week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆5,959Updated last week
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,942Updated 7 months ago
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆2,886Updated 9 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,436Updated this week
- A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations☆16,188Updated this week
- Expert Parallelism Load Balancer☆1,316Updated 8 months ago
- A high-performance distributed file system designed to address the challenges of AI training and inference workloads.☆9,520Updated this week
- SGLang is a fast serving framework for large language models and vision language models.☆21,569Updated this week
- Analyze computation-communication overlap in V3/R1.☆1,125Updated 8 months ago
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,377Updated this week
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.☆3,201Updated this week
- An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & TIS & vLLM & Ray & Dynamic Sampling…☆8,586Updated last week
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆3,252Updated 5 months ago
- OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, …☆6,413Updated last week
- FlashInfer: Kernel Library for LLM Serving☆4,195Updated last week
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,983Updated last year
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,850Updated last year
- Fully open reproduction of DeepSeek-R1☆25,732Updated 3 weeks ago
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆25,791Updated 2 months ago
- Fast and memory-efficient exact attention☆21,067Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,795Updated this week
- Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆17,149Updated 2 weeks ago
- DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding☆5,149Updated 9 months ago
- The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.☆19,953Updated 3 weeks ago
- GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型☆6,961Updated 5 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆17,415Updated last week
- My learning notes for ML SYS.☆4,632Updated this week
- ☆100,727Updated 3 months ago
- Simple RL training for reasoning☆3,808Updated 4 months ago