deepseek-ai / FlashMLALinks
FlashMLA: Efficient Multi-head Latent Attention Kernels
☆11,953Updated 3 weeks 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☆8,862Updated last week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆6,026Updated 2 weeks ago
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,951Updated 7 months ago
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆2,900Updated 9 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,538Updated this week
- Expert Parallelism Load Balancer☆1,329Updated 9 months ago
- A high-performance distributed file system designed to address the challenges of AI training and inference workloads.☆9,569Updated last week
- Analyze computation-communication overlap in V3/R1.☆1,130Updated 9 months ago
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆3,283Updated 6 months ago
- FlashInfer: Kernel Library for LLM Serving☆4,438Updated this week
- High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.☆1,374Updated this week
- A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations☆16,296Updated last week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆22,190Updated this week
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.☆3,340Updated this week
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,988Updated last year
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,466Updated last week
- An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & TIS & vLLM & Ray & Dynamic Sampling…☆8,692Updated 3 weeks ago
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs ( …☆11,983Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆5,716Updated this week
- Democratizing Reinforcement Learning for LLMs☆4,942Updated this week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,030Updated 9 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆4,417Updated this week
- My learning notes for ML SYS.☆4,922Updated this week
- DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding☆5,170Updated 10 months ago
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,863Updated 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…☆3,863Updated 6 months ago
- Community maintained hardware plugin for vLLM on Ascend☆1,532Updated this week
- A lightweight data processing framework built on DuckDB and 3FS.☆4,879Updated 10 months ago
- Simple RL training for reasoning☆3,819Updated 2 weeks ago
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆4,886Updated last month