microsoft / SeerAttentionLinks
SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
☆151Updated last month
Alternatives and similar repositories for SeerAttention
Users that are interested in SeerAttention are comparing it to the libraries listed below
Sorting:
- 16-fold memory access reduction with nearly no loss☆105Updated 5 months ago
- ☆278Updated 2 months ago
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆146Updated 2 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆333Updated 2 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆140Updated 3 months ago
- A sparse attention kernel supporting mix sparse patterns☆294Updated 7 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆239Updated last month
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- ☆141Updated 7 months ago
- ☆118Updated 3 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆138Updated 6 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆226Updated 2 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆323Updated 7 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆490Updated 7 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆187Updated 2 weeks ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆109Updated 5 months ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆93Updated 2 months ago
- Efficient triton implementation of Native Sparse Attention.☆215Updated 3 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆92Updated 2 months ago
- ☆45Updated 9 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆201Updated 7 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆59Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆111Updated 5 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆436Updated last week
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆49Updated 2 months ago
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆45Updated 6 months ago
- Efficient Mixture of Experts for LLM Paper List☆124Updated this week
- ☆124Updated 3 months ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆235Updated 8 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆39Updated last year