microsoft / SeerAttention
SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
☆20Updated 2 weeks ago
Alternatives and similar repositories for SeerAttention:
Users that are interested in SeerAttention are comparing it to the libraries listed below
- TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆24Updated this week
- ☆44Updated 8 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆43Updated 8 months ago
- SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆13Updated 2 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆29Updated 5 months ago
- LLM Inference with Microscaling Format☆11Updated last month
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆59Updated last month
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆32Updated 4 months ago
- 16-fold memory access reduction with nearly no loss☆63Updated last month
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆88Updated 7 months ago
- Code Repository of Evaluating Quantized Large Language Models☆105Updated 3 months ago
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆85Updated this week
- ☆38Updated 2 weeks ago
- Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models☆41Updated last month
- A sparse attention kernel supporting mix sparse patterns☆75Updated 2 months ago
- SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆26Updated 4 months ago
- ☆33Updated 3 weeks ago
- Multi-Candidate Speculative Decoding☆30Updated 7 months ago
- Implementation of Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting☆47Updated 5 months ago
- The official implementation of the DAC 2024 paper GQA-LUT☆11Updated 3 months ago
- [EMNLP 2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization☆25Updated 2 months ago
- The official code for paper "parallel speculative decoding with adaptive draft length."☆29Updated 3 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆21Updated last month
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆45Updated last month
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆151Updated 5 months ago
- Codebase for ICML'24 paper: Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs☆24Updated 5 months ago
- ☆22Updated last month
- ☆13Updated 2 weeks ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆46Updated this week
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆46Updated 2 years ago