Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)
☆369Apr 22, 2025Updated 10 months ago
Alternatives and similar repositories for Spec-Bench
Users that are interested in Spec-Bench are comparing it to the libraries listed below
Sorting:
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,126Jan 24, 2026Updated last month
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,201Feb 20, 2026Updated last week
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆62Feb 21, 2025Updated last year
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆40Feb 13, 2025Updated last year
- Multi-Candidate Speculative Decoding☆39Apr 22, 2024Updated last year
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆214Sep 11, 2025Updated 5 months ago
- Fast inference from large lauguage models via speculative decoding☆888Aug 22, 2024Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆147Dec 23, 2025Updated 2 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆214Feb 13, 2025Updated last year
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆65Jun 26, 2024Updated last year
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,708Jun 25, 2024Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,315Mar 6, 2025Updated 11 months ago
- [ACL2025 Oral🔥]Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling☆22Nov 11, 2025Updated 3 months ago
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆54Mar 14, 2025Updated 11 months ago
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆51Jul 15, 2025Updated 7 months ago
- ☆51Feb 19, 2024Updated 2 years ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆277Aug 31, 2024Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆114Mar 20, 2025Updated 11 months ago
- ☆66Nov 4, 2024Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆144Dec 4, 2024Updated last year
- ☆596Aug 23, 2024Updated last year
- Codes for our paper "Enhancing Continual Relation Extraction via Classifier Decomposition" (Findings of ACL2023)☆10Nov 29, 2023Updated 2 years ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆524Feb 10, 2025Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆358Nov 20, 2025Updated 3 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,190Sep 30, 2025Updated 5 months ago
- ☆221Jan 23, 2025Updated last year
- scalable and robust tree-based speculative decoding algorithm☆370Jan 28, 2025Updated last year
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆504Aug 1, 2024Updated last year
- ☆28May 24, 2025Updated 9 months ago
- ☆64Dec 3, 2024Updated last year
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆74Jul 14, 2025Updated 7 months ago
- official code for GliDe with a CaPE☆20Aug 13, 2024Updated last year
- ☆352Apr 2, 2024Updated last year
- Codes for Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback (ACL 2024 Findings)☆16Jul 2, 2024Updated last year
- Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)☆46Dec 9, 2023Updated 2 years ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆701Feb 14, 2026Updated 2 weeks ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,863Updated this week
- FlashInfer: Kernel Library for LLM Serving☆5,009Feb 23, 2026Updated last week
- ☆39Aug 27, 2024Updated last year