zhuzilin / ring-flash-attention
Ring attention implementation with flash attention
☆578Updated this week
Related projects ⓘ
Alternatives and complementary repositories for ring-flash-attention
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆352Updated last week
- Transformers with Arbitrarily Large Context☆637Updated 2 months ago
- Zero Bubble Pipeline Parallelism☆279Updated this week
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆196Updated 2 months ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆474Updated 2 weeks ago
- Microsoft Automatic Mixed Precision Library☆522Updated last month
- ☆283Updated 7 months ago
- ☆183Updated 6 months ago
- DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆346Updated last week
- A collection of memory efficient attention operators implemented in the Triton language.☆215Updated 5 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆190Updated 2 weeks ago
- Fast inference from large lauguage models via speculative decoding☆562Updated 2 months ago
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆433Updated 2 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆387Updated 3 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆302Updated 2 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆184Updated 3 weeks ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆642Updated last month
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆277Updated 4 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆184Updated 2 weeks ago
- Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)☆815Updated this week
- Latency and Memory Analysis of Transformer Models for Training and Inference☆352Updated 5 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆278Updated 3 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆611Updated 2 months ago
- KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆240Updated 3 weeks ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆163Updated this week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆195Updated last week
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆172Updated last month
- veRL: Volcano Engine Reinforcement Learning for LLM☆279Updated this week
- This repository contains the experimental PyTorch native float8 training UX☆211Updated 3 months ago
- [ICML 2024] CLLMs: Consistency Large Language Models☆350Updated 3 months ago