zhuzilin / ring-flash-attention
Ring attention implementation with flash attention
☆743Updated 2 weeks 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
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆477Updated this week
- Large Context Attention☆704Updated 3 months ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆511Updated 5 months ago
- Microsoft Automatic Mixed Precision Library☆593Updated 6 months ago
- Zero Bubble Pipeline Parallelism☆383Updated 2 weeks ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆715Updated 6 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆209Updated 8 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆240Updated last week
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆297Updated 2 weeks ago
- Fast inference from large lauguage models via speculative decoding☆714Updated 8 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆453Updated 2 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆438Updated 8 months ago
- A PyTorch Native LLM Training Framework☆787Updated 3 months ago
- Distributed Triton for Parallel Systems☆451Updated 2 weeks ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆631Updated last month
- ☆313Updated last year
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆184Updated this week
- A collection of memory efficient attention operators implemented in the Triton language.☆262Updated 10 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆643Updated last month
- A throughput-oriented high-performance serving framework for LLMs☆797Updated 7 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,240Updated last month
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,183Updated this week
- [ICML 2024] CLLMs: Consistency Large Language Models☆391Updated 5 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆120Updated 3 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆258Updated this week
- Best practice for training LLaMA models in Megatron-LM☆649Updated last year
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆190Updated 3 weeks ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆598Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆270Updated 5 months ago
- Scalable toolkit for efficient model alignment☆770Updated this week