deepseek-ai / FlashMLALinks
FlashMLA: Efficient Multi-head Latent Attention Kernels
☆11,886Updated 2 months ago
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☆8,771Updated last week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆5,921Updated last week
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆2,884Updated 8 months ago
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,937Updated 6 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,357Updated this week
- A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations☆15,989Updated this week
- Expert Parallelism Load Balancer☆1,315Updated 8 months ago
- A high-performance distributed file system designed to address the challenges of AI training and inference workloads.☆9,493Updated last month
- Analyze computation-communication overlap in V3/R1.☆1,124Updated 8 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆20,874Updated this week
- verl: Volcano Engine Reinforcement Learning for LLMs☆16,726Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,323Updated this week
- FlashInfer: Kernel Library for LLM Serving☆4,136Updated last week
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.☆3,101Updated this week
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆3,250Updated 4 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆4,054Updated this week
- An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Asy…☆8,476Updated 3 weeks ago
- The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.☆19,844Updated last week
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,971Updated last year
- My learning notes/codes for ML SYS.☆4,323Updated this week
- Democratizing Reinforcement Learning for LLMs☆4,792Updated this week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,007Updated 8 months ago
- Simple RL training for reasoning☆3,796Updated 4 months ago
- OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, …☆6,364Updated this week
- High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.☆1,342Updated 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 (…☆11,418Updated this week
- DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding☆5,131Updated 9 months ago
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,841Updated last year
- GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型☆6,937Updated 5 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆64,235Updated this week