haoliuhl / ringattentionLinks
Large Context Attention
β742Updated 8 months ago
Alternatives and similar repositories for ringattention
Users that are interested in ringattention are comparing it to the libraries listed below
Sorting:
- Implementation of π Ring Attention, from Liu et al. at Berkeley AI, in Pytorchβ539Updated 4 months ago
- Ring attention implementation with flash attentionβ885Updated last month
- Microsoft Automatic Mixed Precision Libraryβ624Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decodingβ1,281Updated 7 months ago
- π Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flashβ¦β269Updated 2 months ago
- Pipeline Parallelism for PyTorchβ781Updated last year
- Scalable toolkit for efficient model alignmentβ842Updated this week
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Trainingβ215Updated last year
- Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4β928Updated this week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.β746Updated last year
- Explorations into some recent techniques surrounding speculative decodingβ288Updated 9 months ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.β577Updated last month
- [ICML 2024] CLLMs: Consistency Large Language Modelsβ403Updated 10 months ago
- Triton-based implementation of Sparse Mixture of Experts.β242Updated last week
- Helpful tools and examples for working with flex-attentionβ1,015Updated last month
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantizationβ385Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantizationβ702Updated last year
- β529Updated 2 weeks ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inferenceβ571Updated 3 weeks ago
- Automatically split your PyTorch models on multiple GPUs for training & inferenceβ655Updated last year
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruningβ630Updated last year
- Zero Bubble Pipeline Parallelismβ428Updated 5 months ago
- Official PyTorch implementation of QA-LoRAβ141Updated last year
- This repository contains the experimental PyTorch native float8 training UXβ223Updated last year
- Serving multiple LoRA finetuned LLM as oneβ1,097Updated last year
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"β382Updated last year
- scalable and robust tree-based speculative decoding algorithmβ359Updated 8 months ago
- π Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.β213Updated last week
- β572Updated last year
- Triton implementation of FlashAttention2 that adds Custom Masks.β138Updated last year