Inteum Company
Links
seedsprint
Visible Legacy
RSS
News & Resources
Inteum Company News
Inteum Library
Subscribe
Search Results - software+%3e+ai
1
Results
Sort By:
Published Date
Updated Date
Title
ID
Descending
Ascending
Quamba2: a robust and scalable post-training quantization framework for selective state space models (SSMs)
Quamba2 highlights Supports W4A8 / W4A16 / W4AX / W8A8 for Mamba1 and Mamba2 Achieves 4x memory reduction and 3x generation speedup Enables 8B model inference on Orin Nano 8G at 13 tokens/sec Outperforms W4A8KV4 Llama3-8B in both speed and quality Background Deploying state space models (SSMs), which excel at processing long sequences but demand...
Published: 4/9/2025
|
Inventor(s):
Diana Marculescu
,
Hung-Yueh Chiang
,
Chi-Chih Chang
,
Natalia Frumkin
,
Mohamed Abdelfattah
,
Kai-Chiang Wu
Keywords(s):
Category(s):
Software > AI
,
Computer > AI/ML > Language processing