hemingkx / SpecDec
Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)
☆39Updated last year
Alternatives and similar repositories for SpecDec:
Users that are interested in SpecDec are comparing it to the libraries listed below
- [ICLR 2024] CLEX: Continuous Length Extrapolation for Large Language Models☆76Updated last year
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆36Updated 11 months ago
- ☆98Updated 5 months ago
- ☆124Updated 8 months ago
- Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"☆73Updated 9 months ago
- [ICLR'25] Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"☆70Updated 4 months ago
- ACL'23: Unified Demonstration Retriever for In-Context Learning☆36Updated last year
- ☆48Updated 11 months ago
- ☆34Updated last year
- LongHeads: Multi-Head Attention is Secretly a Long Context Processor☆29Updated 11 months ago
- Code for M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models☆22Updated 7 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆42Updated last month
- LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation☆20Updated last week
- ☆30Updated last year
- 🍼 Official implementation of Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts☆38Updated 5 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆57Updated 5 months ago
- Code for the ACL-2022 paper "StableMoE: Stable Routing Strategy for Mixture of Experts"☆45Updated 2 years ago
- [ACL 2024 (Oral)] A Prospector of Long-Dependency Data for Large Language Models☆54Updated 8 months ago
- ☆85Updated 2 years ago
- LongMIT: Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets☆35Updated 5 months ago
- ☆31Updated last year
- [NeurIPS 2023] Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective☆30Updated last year
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆55Updated 8 months ago
- One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning☆39Updated last year
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆98Updated last week
- Code for ACL 2023 paper titled "Lifting the Curse of Capacity Gap in Distilling Language Models"☆28Updated last year
- This repository is the official implementation of our EMNLP 2022 paper ELMER: A Non-Autoregressive Pre-trained Language Model for Efficie…☆26Updated 2 years ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆40Updated 4 months ago
- [ACL 2024] Long-Context Language Modeling with Parallel Encodings☆152Updated 9 months ago
- Easy control for Key-Value Constrained Generative LLM Inference(https://arxiv.org/abs/2402.06262)☆60Updated last year