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☆107Updated 4 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
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆201Updated 6 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆59Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆109Updated 5 months ago
- ☆25Updated 3 months ago
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆40Updated last month
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆52Updated 6 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆31Updated 6 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆52Updated last year
- official code for GliDe with a CaPE☆18Updated last year
- ☆56Updated 8 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆62Updated 10 months ago
- [ACL 2024] Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"☆47Updated last year
- Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''☆28Updated 10 months ago
- ☆273Updated last month
- ☆117Updated 2 months ago
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆26Updated 4 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆51Updated 9 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆48Updated last month
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆91Updated 2 months ago
- Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models☆46Updated 9 months ago
- 16-fold memory access reduction with nearly no loss☆104Updated 5 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆62Updated last month
- ☆41Updated 3 months ago
- ☆27Updated 6 months ago
- Unofficial implementations of block/layer-wise pruning methods for LLMs.☆72Updated last year
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆42Updated last year