thunlp / FR-Spec
FR-Spec: Frequency-Ranked Speculative Sampling
☆17Updated last month
Alternatives and similar repositories for FR-Spec:
Users that are interested in FR-Spec are comparing it to the libraries listed below
- ☆39Updated 5 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆47Updated 2 months ago
- ☆22Updated 3 weeks ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆31Updated last week
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆72Updated 3 months ago
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆133Updated last month
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆77Updated last week
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆23Updated 2 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆183Updated 2 months ago
- Multi-Candidate Speculative Decoding☆35Updated last year
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆72Updated last month
- official code for GliDe with a CaPE☆18Updated 8 months ago
- LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification☆50Updated last month
- ☆76Updated last week
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆72Updated this week
- LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation☆23Updated 3 weeks ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆42Updated 3 weeks ago
- ☆74Updated this week
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆51Updated 10 months ago
- ☆49Updated 11 months ago
- ☆22Updated last month
- ☆48Updated 4 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆42Updated 5 months ago
- ☆15Updated 2 months ago
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!☆49Updated 3 weeks ago
- ☆54Updated last week
- ☆12Updated 6 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆175Updated last month
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆45Updated 6 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆57Updated 6 months ago