insuhan / hyper-attnLinks
☆83Updated last year
Alternatives and similar repositories for hyper-attn
Users that are interested in hyper-attn are comparing it to the libraries listed below
Sorting:
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆89Updated 2 months ago
- ☆149Updated 2 years ago
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆70Updated last year
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆240Updated 3 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆84Updated 11 months ago
- Fast and memory-efficient exact attention☆70Updated 7 months ago
- ☆53Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated 11 months ago
- nanoGPT-like codebase for LLM training☆107Updated 4 months ago
- Code for studying the super weight in LLM☆119Updated 10 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆129Updated 9 months ago
- The evaluation framework for training-free sparse attention in LLMs☆98Updated 3 months ago
- Understand and test language model architectures on synthetic tasks.☆229Updated last week
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- ☆122Updated last year
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆81Updated 2 years ago
- Simple and efficient pytorch-native transformer training and inference (batched)☆79Updated last year
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆130Updated 10 months ago
- Experiment of using Tangent to autodiff triton☆81Updated last year
- Repository of the paper "Accelerating Transformer Inference for Translation via Parallel Decoding"☆120Updated last year
- Some preliminary explorations of Mamba's context scaling.☆217Updated last year
- ☆85Updated last year
- Language models scale reliably with over-training and on downstream tasks☆100Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆164Updated 3 months ago
- Here we will test various linear attention designs.☆62Updated last year
- Muon fsdp 2☆44Updated last month
- ☆58Updated last year
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆94Updated last year
- ☆202Updated 9 months ago