zhuzilin / ring-flash-attention
Ring attention implementation with flash attention
β743Updated 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 Inferenceβ477Updated this week
- Large Context Attentionβ704Updated 3 months ago
- Implementation of π Ring Attention, from Liu et al. at Berkeley AI, in Pytorchβ511Updated 5 months ago
- Microsoft Automatic Mixed Precision Libraryβ593Updated 6 months ago
- Zero Bubble Pipeline Parallelismβ383Updated 2 weeks ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.β715Updated 6 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformersβ209Updated 8 months ago
- π Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flashβ¦β240Updated last week
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Frameworkβ297Updated 2 weeks ago
- Fast inference from large lauguage models via speculative decodingβ714Updated 8 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Headsβ453Updated 2 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.β438Updated 8 months ago
- A PyTorch Native LLM Training Frameworkβ787Updated 3 months ago
- Distributed Triton for Parallel Systemsβ451Updated 2 weeks ago
- π³ Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"β631Updated last month
- β313Updated last year
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Trainingβ184Updated this week
- A collection of memory efficient attention operators implemented in the Triton language.β262Updated 10 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Seβ¦β643Updated last month
- A throughput-oriented high-performance serving framework for LLMsβ797Updated 7 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decodingβ1,240Updated last month
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.β1,183Updated this week
- [ICML 2024] CLLMs: Consistency Large Language Modelsβ391Updated 5 months ago
- PyTorch bindings for CUTLASS grouped GEMM.β120Updated 3 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)β258Updated this week
- Best practice for training LLaMA models in Megatron-LMβ649Updated last year
- ByteCheckpoint: An Unified Checkpointing Library for LFMsβ190Updated 3 weeks ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruningβ598Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inferenceβ270Updated 5 months ago
- Scalable toolkit for efficient model alignmentβ770Updated this week