Kaffaljidhmah2 / SpecDec_ppLinks
Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
☆10Updated last month
Alternatives and similar repositories for SpecDec_pp
Users that are interested in SpecDec_pp are comparing it to the libraries listed below
Sorting:
- ☆56Updated 8 months ago
- ☆19Updated 2 years ago
- ☆38Updated last year
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆42Updated last year
- ☆20Updated 2 years ago
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆22Updated 11 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆47Updated 3 weeks ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆103Updated this week
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆49Updated last month
- Python package for rematerialization-aware gradient checkpointing☆26Updated last year
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆90Updated 2 years ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆63Updated last month
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆82Updated 6 months ago
- 16-fold memory access reduction with nearly no loss☆104Updated 5 months ago
- ☆41Updated 3 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆39Updated last year
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆52Updated 9 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆31Updated 6 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- ☆42Updated 2 years ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆108Updated 4 months ago
- ☆74Updated 9 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆59Updated last year
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆76Updated 10 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆48Updated 10 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆58Updated 9 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆155Updated last week
- Kinetics: Rethinking Test-Time Scaling Laws☆79Updated last month
- ☆51Updated last year
- ☆47Updated last year