deepseek-ai / FlashMLALinks
FlashMLA: Efficient MLA kernels
☆11,739Updated 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☆8,564Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆5,752Updated this week
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,922Updated 4 months ago
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.☆2,863Updated 6 months ago
- A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations☆15,102Updated 2 weeks ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,039Updated this week
- A high-performance distributed file system designed to address the challenges of AI training and inference workloads.☆9,341Updated last week
- Expert Parallelism Load Balancer☆1,272Updated 6 months ago
- Analyze computation-communication overlap in V3/R1.☆1,103Updated 6 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆18,528Updated this week
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆3,152Updated 2 months ago
- DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding☆5,060Updated 7 months ago
- FlashInfer: Kernel Library for LLM Serving☆3,829Updated this week
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,939Updated last year
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,801Updated last year
- 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…☆3,668Updated 3 months ago
- MoBA: Mixture of Block Attention for Long-Context LLMs☆1,908Updated 5 months ago
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.☆2,697Updated this week
- verl: Volcano Engine Reinforcement Learning for LLMs☆13,723Updated last week
- A Datacenter Scale Distributed Inference Serving Framework☆5,202Updated this week
- High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.☆1,291Updated this 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 (…☆10,159Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,114Updated this week
- An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Asy…☆8,010Updated last week
- Fully open reproduction of DeepSeek-R1☆25,485Updated 3 weeks ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,793Updated this week
- Democratizing Reinforcement Learning for LLMs☆4,357Updated this week
- A lightweight data processing framework built on DuckDB and 3FS.☆4,788Updated 6 months ago
- Simple RL training for reasoning☆3,754Updated last month
- Fast and memory-efficient exact attention☆19,693Updated this week