hemingkx / SWIFT
SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
☆26Updated last month
Related projects ⓘ
Alternatives and complementary repositories for SWIFT
- Repo for the EMNLP'24 Paper "Dual-Space Knowledge Distillation for Large Language Models".☆37Updated 2 weeks ago
- [ACL 2024 (Oral)] A Prospector of Long-Dependency Data for Large Language Models☆53Updated 3 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆53Updated last month
- ☆31Updated this week
- The official repository of the Omni-MATH benchmark.☆49Updated 2 weeks ago
- LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models☆69Updated last month
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆25Updated 4 months ago
- OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure☆18Updated 3 months ago
- Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"☆67Updated 5 months ago
- Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)☆33Updated 11 months ago
- State-of-the-art Parameter-Efficient MoE Fine-tuning Method☆92Updated 2 months ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆35Updated 7 months ago
- [ICLR 2024] CLEX: Continuous Length Extrapolation for Large Language Models☆73Updated 8 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆118Updated 3 weeks ago
- A method of ensemble learning for heterogeneous large language models.☆30Updated 3 months ago
- Multi-Candidate Speculative Decoding☆28Updated 6 months ago
- Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"☆64Updated last week
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆38Updated this week
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆28Updated 3 weeks ago
- code for ACL24 "MELoRA: Mini-Ensemble Low-Rank Adapter for Parameter-Efficient Fine-Tuning"☆15Updated 6 months ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆97Updated 7 months ago
- One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning☆38Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆76Updated last month
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆138Updated 5 months ago
- ☆15Updated 2 months ago
- A Survey on the Honesty of Large Language Models☆46Updated last month
- We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆51Updated 3 weeks ago
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning"☆91Updated 4 months ago
- A curated list of awesome resources dedicated to Scaling Laws for LLMs☆63Updated last year
- [NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"☆58Updated 11 months ago