DerrickYLJ / TidalDecode
[ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
☆26Updated last month
Alternatives and similar repositories for TidalDecode:
Users that are interested in TidalDecode are comparing it to the libraries listed below
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆64Updated this week
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆31Updated 7 months ago
- 16-fold memory access reduction with nearly no loss☆72Updated 2 months ago
- Quantized Attention on GPU☆34Updated 2 months ago
- ☆23Updated 2 months ago
- LLM Inference with Microscaling Format☆17Updated 2 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆32Updated 5 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆36Updated 2 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆23Updated 2 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆42Updated 3 months ago
- ☆58Updated last week
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆38Updated 11 months ago
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"☆14Updated 3 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆64Updated 4 months ago
- ☆49Updated 8 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆61Updated 2 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆48Updated 7 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆84Updated 3 months ago
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆52Updated last month
- TileFusion is a highly efficient kernel template library designed to elevate the level of abstraction in CUDA C for processing tiles.☆43Updated this week
- ☆51Updated 10 months ago
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆21Updated 4 months ago
- ☆59Updated last month
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆152Updated 6 months ago
- GPTQ inference TVM kernel☆38Updated 9 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆45Updated 10 months ago
- Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models☆41Updated 2 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆64Updated 7 months ago
- A sparse attention kernel supporting mix sparse patterns☆98Updated 3 months ago
- ☆36Updated 5 months ago