FlashMLA: Efficient Multi-head Latent Attention Kernels
☆12,831Jul 28, 2026Updated 2 weeks ago
Alternatives and similar repositories for FlashMLA
Users that are interested in FlashMLA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- DeepEP: an efficient expert-parallel communication library☆9,972Updated this week
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆7,644Jul 20, 2026Updated 3 weeks ago
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆2,989Jan 14, 2026Updated 6 months ago
- Expert Parallelism Load Balancer☆1,417Mar 24, 2025Updated last year
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆8,039May 15, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Analyze computation-communication overlap in V3/R1.☆1,176Mar 21, 2025Updated last year
- A high-performance distributed file system designed to address the challenges of AI training and inference workloads.☆10,107May 7, 2026Updated 3 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,138Updated this week
- Fast and memory-efficient exact attention☆24,672Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆31,578Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,223Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,178Updated this week
- A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations☆19,215Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,900Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,226Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆88,592Updated this week
- Ongoing research training transformer models at scale☆17,387Updated this week
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆14,351Updated this week
- Fully open reproduction of DeepSeek-R1☆26,431Apr 2, 2026Updated 4 months ago
- A lightweight data processing framework built on DuckDB and 3FS.☆4,980Mar 5, 2025Updated last year
- Development repository for the Triton language and compiler☆19,919Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,514Updated this week
- ☆91,976Jun 27, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,352Aug 28, 2025Updated 11 months ago
- 🚀 Efficient implementations for emerging model architectures☆5,536Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,485Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆42,894Updated this week
- slime is an LLM post-training framework for RL Scaling.☆7,832Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,902Jul 14, 2026Updated 3 weeks ago
- ☆104,149Aug 28, 2025Updated 11 months ago
- Muon is Scalable for LLM Training☆1,528Aug 3, 2025Updated last year
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆27,494Jan 9, 2026Updated 7 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A Datacenter Scale Distributed Inference Serving Framework☆7,729Updated this week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,162Apr 3, 2025Updated last year
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,998Updated this week
- Transformer related optimization, including BERT, GPT☆6,445Mar 27, 2024Updated 2 years ago
- Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.☆11,740Updated this week
- Nano vLLM☆14,935Apr 26, 2026Updated 3 months ago
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,216Updated this week