[ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
☆51Jul 15, 2025Updated 7 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:
- ☆20Dec 24, 2024Updated last year
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆54Mar 14, 2025Updated 11 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆40Feb 13, 2025Updated last year
- ☆14Oct 3, 2024Updated last year
- ☆28May 24, 2025Updated 9 months ago
- ☆32Oct 13, 2025Updated 4 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆62Feb 21, 2025Updated last year
- Code repo for efficient quantized MoE inference with mixture of low-rank compensators☆31Apr 14, 2025Updated 10 months ago
- minimal C implementation of speculative decoding based on llama2.c☆25Jul 15, 2024Updated last year
- official code for GliDe with a CaPE☆20Aug 13, 2024Updated last year
- ☆66Nov 4, 2024Updated last year
- Continuous Pipelined Speculative Decoding☆16Jan 4, 2026Updated last month
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆369Apr 22, 2025Updated 10 months ago
- Code for "Adaptive Self-improvement LLM Agentic System for ML Library Development" (ICML 2025)☆15Jan 6, 2026Updated last month
- ☆12Oct 7, 2024Updated last year
- Website for CSE 234, Winter 2025☆13Mar 24, 2025Updated 11 months ago
- Kinetics: Rethinking Test-Time Scaling Laws☆85Jul 11, 2025Updated 7 months ago
- Sequence-level 1F1B schedule for LLMs.☆38Aug 26, 2025Updated 6 months ago
- Official Implementation of APB (ACL 2025 main Oral) and Spava.☆34Jan 30, 2026Updated last month
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆74Jul 14, 2025Updated 7 months ago
- ☆64Dec 3, 2024Updated last year
- An Attention Superoptimizer☆22Jan 20, 2025Updated last year
- [ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference☆49Jun 17, 2025Updated 8 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆154Aug 21, 2025Updated 6 months ago
- Sequence-level 1F1B schedule for LLMs.☆19Jun 4, 2024Updated last year
- Detecting Hallucinations in Large Language Model Generation: A Token Probability Approach. This repository includes the implementation of…☆17Jun 1, 2024Updated last year
- ☆37Sep 13, 2025Updated 5 months ago
- The official implementation of "LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation"☆22Apr 22, 2025Updated 10 months ago
- This is a simple torch implementation of the high performance Multi-Query Attention☆16Aug 23, 2023Updated 2 years ago
- ☆54May 19, 2025Updated 9 months ago
- ☆44Updated this week
- Hydragen: High-Throughput LLM Inference with Shared Prefixes☆48May 10, 2024Updated last year
- ☆43Sep 3, 2025Updated 5 months ago
- ☆22Mar 7, 2025Updated 11 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆147Dec 23, 2025Updated 2 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆144Dec 4, 2024Updated last year
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆55Oct 29, 2024Updated last year
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆138Dec 5, 2025Updated 2 months ago
- ☆41May 27, 2025Updated 9 months ago