zhuzilin / ring-flash-attentionLinks
Ring attention implementation with flash attention
☆957Updated 3 months ago
Alternatives and similar repositories for ring-flash-attention
Users that are interested in ring-flash-attention are comparing it to the libraries listed below
Sorting:
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆619Updated 2 weeks ago
- Large Context Attention☆758Updated 2 months ago
- Zero Bubble Pipeline Parallelism☆444Updated 8 months ago
- Microsoft Automatic Mixed Precision Library☆634Updated last month
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆952Updated 9 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆597Updated last week
- PyTorch bindings for CUTLASS grouped GEMM.☆178Updated 3 weeks ago
- HuggingFace conversion and training library for Megatron-based models☆324Updated this week
- Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs☆915Updated last month
- Fast inference from large lauguage models via speculative decoding☆875Updated last year
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆1,504Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,303Updated last week
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆495Updated last year
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆549Updated 7 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆277Updated last month
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆799Updated 10 months ago
- Scalable toolkit for efficient model alignment☆847Updated 3 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆500Updated last week
- Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4☆953Updated 2 weeks ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆515Updated 10 months ago
- A throughput-oriented high-performance serving framework for LLMs☆929Updated 2 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,312Updated 10 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆347Updated 8 months ago
- A Quirky Assortment of CuTe Kernels☆732Updated this week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆362Updated 5 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆220Updated last year
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆256Updated 4 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆978Updated last year
- ☆351Updated last year
- Pipeline Parallelism for PyTorch☆784Updated last year