cat538 / SKVQ
SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models
☆13Updated 3 months ago
Alternatives and similar repositories for SKVQ:
Users that are interested in SKVQ are comparing it to the libraries listed below
- ☆51Updated 10 months ago
- 16-fold memory access reduction with nearly no loss☆72Updated 2 months ago
- Quantized Attention on GPU☆34Updated 2 months ago
- ☆40Updated last month
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆45Updated 10 months ago
- LLM Inference with Microscaling Format☆17Updated 2 months ago
- A sparse attention kernel supporting mix sparse patterns☆98Updated 3 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆24Updated last month
- Official PyTorch implementation of FlatQuant: Flatness Matters for LLM Quantization☆95Updated last week
- ☆11Updated 7 months ago
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆64Updated this week
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆56Updated last week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆152Updated 6 months ago
- Official implementation of the ICLR 2024 paper AffineQuant☆24Updated 10 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
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"☆14Updated 3 months ago
- Implement some method of LLM KV Cache Sparsity☆30Updated 7 months 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.☆19Updated 10 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆236Updated 2 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆34Updated 2 months ago
- ☆26Updated last week
- ☆82Updated 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
- ☆73Updated 6 months ago
- An algorithm for static activation quantization of LLMs☆112Updated 2 weeks ago
- PyTorch bindings for CUTLASS grouped GEMM.☆61Updated 2 months ago
- ☆59Updated last month
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆95Updated last month
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆98Updated 8 months ago
- Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models☆41Updated 2 months ago