Zyphra / tree_attentionLinks
Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
☆131Updated last year
Alternatives and similar repositories for tree_attention
Users that are interested in tree_attention are comparing it to the libraries listed below
Sorting:
- The evaluation framework for training-free sparse attention in LLMs☆108Updated 2 months ago
- Token Omission Via Attention☆128Updated last year
- ☆47Updated last year
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆157Updated 8 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆243Updated 6 months ago
- RWKV-7: Surpassing GPT☆102Updated last year
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆249Updated 10 months ago
- ☆91Updated last year
- Fast and memory-efficient exact attention☆75Updated 9 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆90Updated 5 months ago
- ☆204Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated last year
- Understand and test language model architectures on synthetic tasks.☆247Updated 3 months ago
- Normalized Transformer (nGPT)☆194Updated last year
- ☆54Updated last year
- Work in progress.☆75Updated last month
- Official implementation for Training LLMs with MXFP4☆116Updated 8 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆135Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆146Updated last year
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆162Updated 8 months ago
- Some preliminary explorations of Mamba's context scaling.☆218Updated last year
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆133Updated last month
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆223Updated 6 months ago
- ☆113Updated last month
- Simple and efficient pytorch-native transformer training and inference (batched)☆79Updated last year
- PyTorch implementation of models from the Zamba2 series.☆186Updated 11 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆127Updated 6 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆181Updated 6 months ago
- Linear Attention Sequence Parallelism (LASP)☆88Updated last year
- ☆71Updated last year