Jingyu6 / speculative_prefillLinks
☆32Updated last month
Alternatives and similar repositories for speculative_prefill
Users that are interested in speculative_prefill are comparing it to the libraries listed below
Sorting:
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆41Updated 2 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆28Updated 5 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆41Updated last year
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆80Updated 4 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆125Updated 4 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆57Updated 4 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆40Updated 2 months ago
- ☆136Updated 5 months ago
- Multi-Candidate Speculative Decoding☆35Updated last year
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆37Updated 11 months ago
- ☆54Updated 7 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆46Updated 8 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆107Updated 3 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆49Updated 7 months ago
- ☆109Updated last month
- 16-fold memory access reduction with nearly no loss☆100Updated 3 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆47Updated 8 months ago
- ☆116Updated last month
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆93Updated 3 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆194Updated 5 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆60Updated 9 months ago
- ☆38Updated 10 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆118Updated last month
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆58Updated last year
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆71Updated 3 months ago
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆22Updated 10 months ago
- ☆43Updated 7 months ago
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆36Updated 2 weeks ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆82Updated 3 weeks ago