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
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆36Updated 11 months ago
- ☆96Updated 5 months ago
- [ICLR 2024] CLEX: Continuous Length Extrapolation for Large Language Models☆76Updated last year
- [ICLR'25] Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"☆70Updated 3 months ago
- LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation☆20Updated last week
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆40Updated 2 weeks ago
- Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"☆72Updated 9 months ago
- ☆20Updated 2 years ago
- 🍼 Official implementation of Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts☆38Updated 5 months ago
- ☆47Updated 11 months ago
- We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆60Updated 4 months ago
- Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process☆24Updated 7 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆39Updated 4 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆162Updated this week
- Towards Systematic Measurement for Long Text Quality☆32Updated 6 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆56Updated 5 months ago
- ACL'23: Unified Demonstration Retriever for In-Context Learning☆36Updated last year
- ☆34Updated 11 months ago
- ☆123Updated 7 months ago
- Suri: Multi-constraint instruction following for long-form text generation (EMNLP’24)☆22Updated 4 months ago
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆54Updated 8 months ago
- [ACL 2024 (Oral)] A Prospector of Long-Dependency Data for Large Language Models☆54Updated 7 months ago
- Code for preprint "Metadata Conditioning Accelerates Language Model Pre-training (MeCo)"☆36Updated 2 months ago
- Code for paper "Patch-Level Training for Large Language Models"☆81Updated 3 months ago
- [ACL 2024] Long-Context Language Modeling with Parallel Encodings☆153Updated 8 months ago
- Code for our EMNLP-2023 paper: "Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks"☆24Updated last year
- ☆30Updated last year
- Retrieval as Attention☆83Updated 2 years ago
- Sparse Backpropagation for Mixture-of-Expert Training☆28Updated 8 months ago