hemingkx / SpecDecLinks
Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)
☆42Updated last year
Alternatives and similar repositories for SpecDec
Users that are interested in SpecDec are comparing it to the libraries listed below
Sorting:
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆38Updated last year
- ☆139Updated last year
- [ACL 2024] Long-Context Language Modeling with Parallel Encodings☆157Updated last year
- ☆53Updated last year
- ☆103Updated 2 weeks ago
- [ICLR 2024] CLEX: Continuous Length Extrapolation for Large Language Models☆78Updated last year
- A curated list of awesome resources dedicated to Scaling Laws for LLMs☆76Updated 2 years ago
- [ICLR'25] Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"☆77Updated 8 months ago
- This PyTorch package implements MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation (NAACL 2022).☆109Updated 3 years ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆61Updated 10 months ago
- Code for ICML 25 paper "Metadata Conditioning Accelerates Language Model Pre-training (MeCo)"☆41Updated last month
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆49Updated 9 months ago
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆75Updated 2 months ago
- [EMNLP 2023]Context Compression for Auto-regressive Transformers with Sentinel Tokens☆25Updated last year
- ☆35Updated last year
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆62Updated last year
- One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning☆40Updated 2 years ago
- 🍼 Official implementation of Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts☆39Updated 10 months ago
- Code for the ACL-2022 paper "StableMoE: Stable Routing Strategy for Mixture of Experts"☆47Updated 3 years ago
- LongMIT: Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets☆36Updated 10 months ago
- [ACL 2024 (Oral)] A Prospector of Long-Dependency Data for Large Language Models☆56Updated last year
- [ACL 2025, Main Conference, Oral] Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process☆28Updated last year
- [NeurIPS 2023] Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective☆33Updated last year
- The official implementation for Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free☆46Updated 2 months ago
- ACL'23: Unified Demonstration Retriever for In-Context Learning☆38Updated last year
- Towards Systematic Measurement for Long Text Quality☆37Updated 10 months ago
- [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆63Updated 9 months ago
- Code for the preprint "Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?"☆41Updated this week
- [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…☆53Updated 2 years ago
- Long Context Extension and Generalization in LLMs☆58Updated 10 months ago