NJUNLP / MCSDLinks
Multi-Candidate Speculative Decoding
☆36Updated last year
Alternatives and similar repositories for MCSD
Users that are interested in MCSD are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆117Updated 5 months ago
- ☆45Updated 10 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆99Updated last week
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆202Updated 7 months ago
- official code for GliDe with a CaPE☆18Updated last year
- ☆28Updated 4 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆32Updated 7 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆60Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆110Updated 6 months ago
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆44Updated 2 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆55Updated 7 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆52Updated last year
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆63Updated last year
- ☆280Updated 2 months ago
- ☆58Updated 10 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆51Updated 11 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- ☆119Updated 3 months ago
- ☆52Updated last year
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆85Updated 7 months ago
- ☆43Updated 4 months ago
- ☆56Updated last year
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆94Updated 3 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆49Updated 11 months ago
- ☆77Updated 11 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference