deepseek-ai / FlashMLALinks
FlashMLA: Efficient MLA decoding kernels
☆11,607Updated last month
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☆7,911Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆5,450Updated this week
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,824Updated last month
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.☆2,807Updated 3 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆3,436Updated this week
- A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations☆14,423Updated this week
- Expert Parallelism Load Balancer☆1,209Updated 2 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆15,276Updated this week
- DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding☆4,894Updated 3 months ago
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,909Updated 8 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆9,710Updated this week
- A high-performance distributed file system designed to address the challenges of AI training and inference workloads.☆9,022Updated this week
- Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆10,997Updated last month
- Analyze computation-communication overlap in V3/R1.☆1,059Updated 3 months ago
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆22,102Updated last week
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,723Updated last year
- FlashInfer: Kernel Library for LLM Serving☆3,211Updated this week
- Janus-Series: Unified Multimodal Understanding and Generation Models☆17,380Updated 4 months ago
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆6,517Updated last week
- 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…☆3,149Updated last week
- An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Asy…☆7,075Updated last week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆49,721Updated this week
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.☆9,608Updated this week
- Fully open reproduction of DeepSeek-R1☆24,819Updated 2 weeks ago
- Simple RL training for reasoning☆3,627Updated 2 months ago
- The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.☆18,509Updated this week
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-…☆8,168Updated this week
- A lightweight data processing framework built on DuckDB and 3FS.☆4,697Updated 3 months ago
- Minimal reproduction of DeepSeek R1-Zero☆11,909Updated last month
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆2,791Updated last week