deepseek-ai / FlashMLALinks
FlashMLA: Efficient Multi-head Latent Attention Kernels
☆11,964Updated 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☆8,875Updated 2 weeks ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆6,052Updated last week
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆2,901Updated 10 months ago
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,950Updated 8 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,565Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆22,343Updated this week
- Expert Parallelism Load Balancer☆1,333Updated 9 months ago
- A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations☆16,344Updated this week
- Analyze computation-communication overlap in V3/R1.☆1,133Updated 9 months ago
- A high-performance distributed file system designed to address the challenges of AI training and inference workloads.☆9,603Updated last week
- FlashInfer: Kernel Library for LLM Serving☆4,626Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,521Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆4,605Updated this week
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (…☆12,112Updated this week
- Fast and memory-efficient exact attention☆21,635Updated this week
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.☆3,381Updated this week
- Fully open reproduction of DeepSeek-R1☆25,805Updated last month
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,989Updated last year
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,835Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆8,793Updated last week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,031Updated 9 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆18,310Updated this week
- OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, …☆6,551Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆67,633Updated this week
- My learning notes for ML SYS.☆5,024Updated last week
- A Datacenter Scale Distributed Inference Serving Framework☆5,759Updated this week
- Simple RL training for reasoning☆3,826Updated 3 weeks ago
- 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉☆9,295Updated last week
- High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.☆1,381Updated last week
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆3,298Updated 6 months ago