haoliuhl / ringattentionLinks
Large Context Attention
β720Updated 6 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 Pytorchβ533Updated 2 months ago
- Ring attention implementation with flash attentionβ831Updated this week
- Microsoft Automatic Mixed Precision Libraryβ616Updated 10 months ago
- π Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flashβ¦β258Updated 2 weeks ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decodingβ1,267Updated 5 months ago
- Explorations into some recent techniques surrounding speculative decodingβ278Updated 7 months ago
- Scalable toolkit for efficient model alignmentβ834Updated last week
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Trainingβ213Updated 11 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.β739Updated 10 months ago
- [ICML 2024] CLLMs: Consistency Large Language Modelsβ397Updated 8 months ago
- Scalable toolkit for efficient model reinforcementβ578Updated this week
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantizationβ367Updated 11 months ago
- Triton-based implementation of Sparse Mixture of Experts.β230Updated 8 months ago
- Tutel MoE: Optimized Mixture-of-Experts Library, Support DeepSeek/Kimi-K2/Qwen3 FP8/FP4β870Updated last week
- LLM KV cache compression made easyβ570Updated this week
- Pipeline Parallelism for PyTorchβ775Updated 11 months ago
- Official PyTorch implementation of QA-LoRAβ138Updated last year
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"β376Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantizationβ698Updated 11 months ago
- This repository contains the experimental PyTorch native float8 training UXβ224Updated last year
- β510Updated last week
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruningβ626Updated last year
- Zero Bubble Pipeline Parallelismβ415Updated 3 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inferenceβ541Updated 3 weeks ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.β567Updated this week
- Helpful tools and examples for working with flex-attentionβ908Updated 3 weeks ago
- Automatically split your PyTorch models on multiple GPUs for training & inferenceβ656Updated last year
- Megatron's multi-modal data loaderβ232Updated last week
- The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reductionβ388Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Headsβ483Updated 6 months ago