zhuzilin / ring-flash-attentionLinks
Ring attention implementation with flash attention
☆831Updated last week
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☆541Updated 3 weeks ago
- Large Context Attention☆720Updated 6 months ago
- Microsoft Automatic Mixed Precision Library☆616Updated 10 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆803Updated 4 months ago
- Zero Bubble Pipeline Parallelism☆415Updated 3 months ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆468Updated this week
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆536Updated 2 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆465Updated last year
- Scalable toolkit for efficient model reinforcement☆578Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆483Updated 6 months ago
- Fast inference from large lauguage models via speculative decoding☆795Updated 11 months ago
- A throughput-oriented high-performance serving framework for LLMs☆862Updated last month
- A PyTorch Native LLM Training Framework☆843Updated last month
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,267Updated 5 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆281Updated this week
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆213Updated 11 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆731Updated 5 months ago
- Distributed Compiler based on Triton for Parallel Systems☆941Updated last week
- LLM KV cache compression made easy☆570Updated this week
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆258Updated 2 weeks ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,462Updated this week
- ☆331Updated last year
- slime is a LLM post-training framework aiming for RL Scaling.☆1,113Updated this week
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆303Updated 3 months ago
- Tutel MoE: Optimized Mixture-of-Experts Library, Support DeepSeek/Kimi-K2/Qwen3 FP8/FP4☆870Updated last week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆739Updated 10 months ago
- Scalable toolkit for efficient model alignment☆834Updated last week
- PyTorch bindings for CUTLASS grouped GEMM.☆134Updated 3 weeks ago
- A collection of memory efficient attention operators implemented in the Triton language.☆275Updated last year
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆230Updated last month