NJUNLP / MCSDLinks
Multi-Candidate Speculative Decoding
☆35Updated last year
Alternatives and similar repositories for MCSD
Users that are interested in MCSD are comparing it to the libraries listed below
Sorting:
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆76Updated 4 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆83Updated last month
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆57Updated 11 months ago
- ☆42Updated 6 months ago
- ☆54Updated last year
- ☆50Updated 6 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆50Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆186Updated 3 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆45Updated 7 months ago
- ☆93Updated 2 weeks ago
- ☆23Updated last week
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆106Updated 2 months ago
- official code for GliDe with a CaPE☆19Updated 9 months ago
- ☆49Updated last year
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆28Updated 3 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆39Updated last month
- Implement some method of LLM KV Cache Sparsity☆32Updated 11 months ago
- ☆28Updated 2 weeks ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆49Updated 3 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆60Updated 8 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆86Updated 2 years ago
- Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"☆44Updated last year
- (ACL 2025 main) FR-Spec: Frequency-Ranked Speculative Sampling☆26Updated this week
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆46Updated 7 months ago
- Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''☆25Updated 7 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆37Updated 2 weeks ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆39Updated 11 months ago
- ☆248Updated last year
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"☆19Updated 7 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆163Updated 10 months ago