deepseek-ai / FlashMLALinks
FlashMLA: Efficient MLA decoding kernels
☆11,570Updated 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☆7,701Updated last week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆5,376Updated last week
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.☆2,784Updated 2 months ago
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,779Updated 2 weeks ago
- Expert Parallelism Load Balancer☆1,199Updated 2 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆14,667Updated this week
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆21,673Updated last week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆3,331Updated this week
- DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding☆4,854Updated 3 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆8,593Updated this week
- Analyze computation-communication overlap in V3/R1.☆1,040Updated 2 months ago
- A high-performance distributed file system designed to address the challenges of AI training and inference workloads.☆8,934Updated last week
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,895Updated 8 months ago
- Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆10,709Updated 2 weeks ago
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.☆8,967Updated last week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆48,531Updated this week
- Fully open reproduction of DeepSeek-R1☆24,541Updated this week
- A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations☆14,176Updated this week
- FlashInfer: Kernel Library for LLM Serving☆3,044Updated this week
- The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.☆18,358Updated last month
- An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & RFT & Dynamic Sampling & Asy…☆6,880Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆6,427Updated this week
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆2,715Updated 2 weeks ago
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-…☆7,769Updated this week
- Janus-Series: Unified Multimodal Understanding and Generation Models☆17,306Updated 3 months ago
- Simple RL training for reasoning☆3,584Updated last month
- Solve Visual Understanding with Reinforced VLMs☆4,990Updated 2 weeks 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…☆3,042Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆4,103Updated last week
- DeepSeek LLM: Let there be answers☆6,393Updated last year