zhuzilin / ring-flash-attentionLinks
Ring attention implementation with flash attention
☆789Updated 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☆519Updated 3 weeks ago
- Large Context Attention☆716Updated 5 months ago
- Zero Bubble Pipeline Parallelism☆398Updated last month
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆519Updated last month
- Microsoft Automatic Mixed Precision Library☆609Updated 8 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆253Updated this week
- Fast inference from large lauguage models via speculative decoding☆762Updated 10 months ago
- Distributed Compiler Based on Triton for Parallel Systems☆829Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆705Updated 3 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆454Updated 10 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆702Updated 3 months ago
- Scalable toolkit for efficient model reinforcement☆438Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆825Updated 2 weeks ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆209Updated last week
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆210Updated 10 months ago
- LLM KV cache compression made easy☆520Updated this week
- A PyTorch Native LLM Training Framework☆821Updated 5 months ago
- ☆328Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,325Updated 2 weeks ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆355Updated last month
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,258Updated 3 months ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆459Updated this week
- Helpful tools and examples for working with flex-attention☆831Updated 2 weeks ago
- slime is a LLM post-training framework aiming at scaling RL.☆328Updated this week
- A collection of memory efficient attention operators implemented in the Triton language.☆272Updated last year
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆800Updated last week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆297Updated 7 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆282Updated 2 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆359Updated 10 months ago
- Scalable toolkit for efficient model alignment☆814Updated 3 weeks ago