HKUDS/SepLLM

[ICML 2025] "SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator"

36
/ 100
Emerging

This project helps data scientists and AI/ML engineers make large language models (LLMs) run much faster and use less memory, especially for long texts. By identifying and compressing less important parts of the text into 'separator' tokens, it reduces the computational load. This means you can process longer documents or complex queries more efficiently, making LLMs more practical for real-world applications.

567 stars. No commits in the last 6 months.

Use this if you are a developer or researcher working with large language models and need to improve their inference speed, reduce memory usage (KV cache), or handle extremely long text sequences in applications like advanced chatbots or document analysis.

Not ideal if you are an end-user simply looking to use an existing LLM or if your primary concern is fine-tuning small models where efficiency is not a critical bottleneck.

natural-language-processing large-language-models computational-efficiency AI-inference-optimization streaming-NLP
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

567

Forks

46

Language

Python

License

Last pushed

Jul 29, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/HKUDS/SepLLM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.