andy-yang-1 / DoubleSparse
16-fold memory access reduction with nearly no loss
☆81Updated this week
Alternatives and similar repositories for DoubleSparse:
Users that are interested in DoubleSparse are comparing it to the libraries listed below
- A sparse attention kernel supporting mix sparse patterns☆164Updated last month
- ☆52Updated 11 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆51Updated 8 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆259Updated 4 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆157Updated 8 months ago
- ☆231Updated 10 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆110Updated 3 months ago
- ☆47Updated 3 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆47Updated 11 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆34Updated 7 months ago
- [ICLR 2025] PEARL: parallel speculative decoding with adaptive draft length☆59Updated last week
- ☆64Updated 2 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆89Updated last month
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆66Updated 2 months ago
- SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆28Updated 7 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆43Updated 5 months ago
- ☆116Updated last month
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆30Updated 3 weeks ago
- [ICLR 2024] Jaiswal, A., Gan, Z., Du, X., Zhang, B., Wang, Z., & Yang, Y. Compressing llms: The truth is rarely pure and never simple.☆21Updated last year
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆47Updated 8 months ago
- ☆64Updated 3 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆71Updated 6 months ago
- ☆24Updated 4 months ago
- Quantized Attention on GPU☆45Updated 4 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆121Updated last month
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆59Updated 5 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆74Updated 4 months ago
- ☆39Updated 8 months ago