haoliuhl / ringattention
Large Context Attention
☆685Updated last month
Alternatives and similar repositories for ringattention:
Users that are interested in ringattention are comparing it to the libraries listed below
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆503Updated 4 months ago
- Ring attention implementation with flash attention☆692Updated last week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,198Updated 4 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆223Updated this week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆702Updated 5 months ago
- Helpful tools and examples for working with flex-attention☆662Updated last week
- Triton-based implementation of Sparse Mixture of Experts.☆201Updated 3 months ago
- Microsoft Automatic Mixed Precision Library☆574Updated 5 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆587Updated 11 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆335Updated 6 months ago
- Scalable toolkit for efficient model alignment☆735Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆440Updated last week
- Explorations into some recent techniques surrounding speculative decoding☆243Updated 2 months ago
- [ICML 2024] CLLMs: Consistency Large Language Models☆377Updated 3 months ago
- Official PyTorch implementation of QA-LoRA☆127Updated 11 months ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆515Updated last week
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆206Updated 6 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆740Updated 5 months ago
- Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)☆990Updated last week
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆678Updated 6 months ago
- ☆217Updated 8 months ago
- For releasing code related to compression methods for transformers, accompanying our publications☆409Updated last month
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆362Updated last year
- This repository contains the experimental PyTorch native float8 training UX☆221Updated 7 months ago
- A simple and effective LLM pruning approach.☆713Updated 6 months ago
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆391Updated 4 months ago
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆268Updated last year
- Zero Bubble Pipeline Parallelism☆345Updated 2 weeks ago
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆770Updated 6 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆559Updated last week