zhuzilin / ring-flash-attention
Ring attention implementation with flash attention
☆759Updated last month
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☆492Updated 3 weeks ago
- Large Context Attention☆710Updated 3 months ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆512Updated 6 months ago
- Microsoft Automatic Mixed Precision Library☆595Updated 7 months ago
- Zero Bubble Pipeline Parallelism☆389Updated last week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆723Updated 7 months ago
- Fast inference from large lauguage models via speculative decoding☆723Updated 8 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆653Updated last month
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆444Updated 9 months ago
- Distributed Triton for Parallel Systems☆677Updated last week
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆209Updated 8 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆244Updated this week
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆714Updated last week
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆308Updated last month
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,246Updated 2 months ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,220Updated last week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆457Updated 3 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆190Updated 3 weeks ago
- A throughput-oriented high-performance serving framework for LLMs☆806Updated this week
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆828Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆666Updated 2 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆121Updated 4 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆279Updated 5 months ago
- Helpful tools and examples for working with flex-attention☆766Updated last week
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆608Updated last year
- A collection of memory efficient attention operators implemented in the Triton language.☆266Updated 11 months ago
- ☆319Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆818Updated 8 months ago
- Explorations into some recent techniques surrounding speculative decoding☆262Updated 4 months ago
- Applied AI experiments and examples for PyTorch☆265Updated 2 weeks ago