[ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
☆54Jul 15, 2025Updated 8 months ago
Alternatives and similar repositories for FR-Spec
Users that are interested in FR-Spec are comparing it to the libraries listed below
Sorting:
- ☆14Oct 3, 2024Updated last year
- ☆19Dec 24, 2024Updated last year
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆54Mar 14, 2025Updated last year
- Sequence-level 1F1B schedule for LLMs.☆38Aug 26, 2025Updated 6 months ago
- Sequence-level 1F1B schedule for LLMs.☆19Jun 4, 2024Updated last year
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆45Feb 13, 2025Updated last year
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆65Feb 21, 2025Updated last year
- Official Implementation of APB (ACL 2025 main Oral) and Spava.☆35Jan 30, 2026Updated last month
- ☆28May 24, 2025Updated 9 months ago
- ☆64Dec 3, 2024Updated last year
- ☆33Oct 13, 2025Updated 5 months ago
- official code for GliDe with a CaPE☆20Aug 13, 2024Updated last year
- ☆67Nov 4, 2024Updated last year
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆372Apr 22, 2025Updated 11 months ago
- minimal C implementation of speculative decoding based on llama2.c☆28Jul 15, 2024Updated last year
- ☆39Sep 13, 2025Updated 6 months ago
- Kinetics: Rethinking Test-Time Scaling Laws☆86Jul 11, 2025Updated 8 months ago
- Fourier Controller Networks (FCNet) for Real-Time Decision-Making in Embodied Learning, ICML 2024☆31Jan 2, 2025Updated last year
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆76Jul 14, 2025Updated 8 months ago
- Cascade Speculative Drafting☆33Apr 2, 2024Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆144Dec 4, 2024Updated last year
- [ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference☆50Jun 17, 2025Updated 9 months ago
- WIKIGENBENCH: Exploring Full-length Wikipedia Generation under Real-World Scenario (COLING 2025)☆12Jan 5, 2025Updated last year
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆156Feb 27, 2026Updated 3 weeks ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆117Mar 20, 2025Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆155Aug 21, 2025Updated 7 months ago
- An Attention Superoptimizer☆22Jan 20, 2025Updated last year
- ☆56May 19, 2025Updated 10 months ago
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆236Jan 14, 2026Updated 2 months ago
- Continuous Pipelined Speculative Decoding☆18Jan 4, 2026Updated 2 months ago
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,145Mar 9, 2026Updated last week
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆151Dec 23, 2025Updated 2 months ago
- ☆26Mar 14, 2024Updated 2 years ago
- Code repo for efficient quantized MoE inference with mixture of low-rank compensators☆34Apr 14, 2025Updated 11 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆215Mar 5, 2026Updated 2 weeks ago
- [AAAI26] LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs☆55Dec 7, 2025Updated 3 months ago
- [ICML‘2024] "LoCoCo: Dropping In Convolutions for Long Context Compression", Ruisi Cai, Yuandong Tian, Zhangyang Wang, Beidi Chen☆17Sep 7, 2024Updated last year
- ☆32Nov 18, 2025Updated 4 months ago
- The user library, public☆11Jun 29, 2023Updated 2 years ago