microsoft / SeerAttention
SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
☆23Updated 2 months ago
Alternatives and similar repositories for SeerAttention:
Users that are interested in SeerAttention are comparing it to the libraries listed below
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆26Updated last month
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆31Updated 7 months ago
- Code release for AdapMoE accepted by ICCAD 2024☆10Updated 3 months ago
- 16-fold memory access reduction with nearly no loss☆72Updated 2 months ago
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆52Updated last month
- ☆51Updated 10 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆24Updated last month
- LLM Inference with Microscaling Format☆17Updated 2 months ago
- ☆40Updated last month
- SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆13Updated 3 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
- Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models☆41Updated 2 months ago
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆64Updated this week
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆45Updated 10 months ago
- ☆11Updated 7 months ago
- Implement some method of LLM KV Cache Sparsity☆30Updated 7 months ago
- The official implementation of the DAC 2024 paper GQA-LUT☆11Updated last month
- Multi-Candidate Speculative Decoding☆34Updated 9 months ago
- SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆26Updated 5 months ago
- Quantized Attention on GPU☆34Updated 2 months ago
- A sparse attention kernel supporting mix sparse patterns☆98Updated 3 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆56Updated last week
- ☆45Updated 3 weeks ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆115Updated last week
- [ICLR 2025] PEARL: parallel speculative decoding with adaptive draft length☆32Updated 5 months ago
- ☆23Updated 2 months ago
- ☆49Updated 8 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆36Updated 2 months ago
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆16Updated 7 months ago
- Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs☆15Updated last month