haoliuhl / ringattention
Large Context Attention
β696Updated 2 months ago
Alternatives and similar repositories for ringattention:
Users that are interested in ringattention are comparing it to the libraries listed below
- Implementation of π Ring Attention, from Liu et al. at Berkeley AI, in Pytorchβ509Updated 5 months ago
- Ring attention implementation with flash attentionβ721Updated last month
- π Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flashβ¦β234Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decodingβ1,221Updated 3 weeks ago
- Microsoft Automatic Mixed Precision Libraryβ587Updated 6 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.β706Updated 6 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inferenceβ463Updated 2 weeks ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformersβ207Updated 7 months ago
- Helpful tools and examples for working with flex-attentionβ701Updated 2 weeks ago
- [ICML 2024] CLLMs: Consistency Large Language Modelsβ388Updated 4 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantizationβ337Updated 7 months ago
- Explorations into some recent techniques surrounding speculative decodingβ250Updated 3 months ago
- β141Updated last year
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruningβ598Updated last year
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.β524Updated last month
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.β1,113Updated last week
- Triton-based implementation of Sparse Mixture of Experts.β209Updated 4 months ago
- This repository contains the experimental PyTorch native float8 training UXβ222Updated 8 months ago
- Zero Bubble Pipeline Parallelismβ379Updated 3 weeks ago
- Scalable toolkit for efficient model alignmentβ756Updated 2 weeks ago
- Official PyTorch implementation of QA-LoRAβ129Updated last year
- LLM KV cache compression made easyβ444Updated 2 weeks ago
- β311Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.β783Updated 6 months ago
- Pipeline Parallelism for PyTorchβ761Updated 7 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.β433Updated 8 months ago
- Multipack distributed sampler for fast padding-free training of LLMsβ186Updated 7 months ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantizationβ683Updated 7 months ago
- Triton implementation of FlashAttention2 that adds Custom Masks.β106Updated 7 months ago
- Automatically split your PyTorch models on multiple GPUs for training & inferenceβ651Updated last year