zhzihao / QPruningKV
More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression
☆11Updated 4 months ago
Alternatives and similar repositories for QPruningKV
Users that are interested in QPruningKV are comparing it to the libraries listed below
Sorting:
- ☆82Updated last week
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆74Updated 3 months ago
- ☆40Updated 5 months ago
- LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification☆53Updated 2 months ago
- Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"☆44Updated 11 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆26Updated 3 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆44Updated 6 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆47Updated 5 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆45Updated 6 months ago
- SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆19Updated 7 months ago
- ☆9Updated 8 months ago
- ☆49Updated last year
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆37Updated 10 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆47Updated 2 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆103Updated this week
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆34Updated 3 weeks ago
- Multi-Candidate Speculative Decoding☆35Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆81Updated last month
- ☆19Updated 4 months ago
- LLM Inference with Microscaling Format☆22Updated 6 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆49Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆36Updated 3 weeks ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆37Updated 9 months ago
- ☆79Updated 3 weeks ago
- qwen-nsa☆61Updated last month
- ☆49Updated 5 months ago
- official code for GliDe with a CaPE☆19Updated 9 months ago
- 16-fold memory access reduction with nearly no loss☆93Updated last month
- ☆39Updated last month
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆38Updated last year