https://github.com/hkuds/sepllm
[ICML 2025] "SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator"
https://github.com/hkuds/sepllm
inference-speed large-language-models llms
Last synced: 3 months ago
JSON representation
[ICML 2025] "SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator"
- Host: GitHub
- URL: https://github.com/hkuds/sepllm
- Owner: HKUDS
- Created: 2024-12-11T15:16:27.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2025-07-02T12:39:58.000Z (3 months ago)
- Last Synced: 2025-07-02T13:45:29.771Z (3 months ago)
- Topics: inference-speed, large-language-models, llms
- Language: Python
- Homepage: https://arxiv.org/abs/2412.12094
- Size: 502 MB
- Stars: 100
- Watchers: 0
- Forks: 6
- Open Issues: 0
-
Metadata Files:
- Readme: README.md