sail-sg / SimLayerKVLinks
The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
☆48Updated 10 months ago
Alternatives and similar repositories for SimLayerKV
Users that are interested in SimLayerKV are comparing it to the libraries listed below
Sorting:
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆31Updated 6 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆51Updated 9 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆62Updated last month
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆109Updated 5 months ago
- ☆45Updated 9 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆89Updated 2 months ago
- ☆139Updated 6 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆124Updated 8 months ago
- ☆85Updated 7 months ago
- ☆20Updated 4 months ago
- ☆117Updated 2 months ago
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆72Updated 5 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆52Updated 6 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆38Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆133Updated 3 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆51Updated 9 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- ☆41Updated 3 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆48Updated last month
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆42Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆45Updated 2 weeks ago
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"☆23Updated 10 months ago
- 16-fold memory access reduction with nearly no loss☆104Updated 4 months ago
- ☆51Updated 2 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆59Updated last year
- ☆273Updated last month
- Long Context Extension and Generalization in LLMs☆58Updated 11 months ago
- (ACL 2025 oral) SCOPE: Optimizing KV Cache Compression in Long-context Generation☆32Updated 2 months ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆91Updated 2 months ago
- Kinetics: Rethinking Test-Time Scaling Laws☆76Updated last month