zhuzilin / ring-flash-attention
Ring attention implementation with flash attention
☆660Updated 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
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆415Updated 3 weeks ago
- Large Context Attention☆677Updated this week
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆498Updated 3 months ago
- Zero Bubble Pipeline Parallelism☆317Updated 2 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆204Updated 5 months ago
- Microsoft Automatic Mixed Precision Library☆553Updated 4 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆419Updated 5 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆216Updated this week
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆492Updated this week
- ☆311Updated 9 months ago
- Efficient LLM Inference over Long Sequences☆349Updated last month
- ☆217Updated 8 months ago
- Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)☆928Updated 3 weeks ago
- DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆420Updated last week
- Helpful tools and examples for working with flex-attention☆603Updated this week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆694Updated 4 months ago
- Fast inference from large lauguage models via speculative decoding☆643Updated 5 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆327Updated 5 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆689Updated 4 months ago
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆567Updated this week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆235Updated 2 months ago
- Scalable toolkit for efficient model alignment☆693Updated this week
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆186Updated last week
- A collection of memory efficient attention operators implemented in the Triton language.☆233Updated 7 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆291Updated 6 months ago
- A throughput-oriented high-performance serving framework for LLMs☆714Updated 4 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆273Updated last month
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,183Updated 3 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆194Updated 2 months ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆276Updated 2 weeks ago