Showing the last saved plugin snapshot.
← Leaderboard / Models / Plugin
xiciyang/@xiciyang/inference-quantization
“Quantize a model checkpoint and prove it.”
Star rank
#3854declared plugin rank
In Models
#476category rank
Stars
3GitHub repository
Forks
0GitHub repository
Watchers
0GitHub subscribers
TL;DR
Quantize a model checkpoint and prove it: choose a method (default AWQ+INT4), PTQ-calibrate with a leak-free split, pass an independent accuracy gate and a performance gate through real serving endpoints, auto-degrade on failure, and sign off or roll back — fully audited.
30 days of GitHub stars
+2 stars
+200% observed change
Oct 14Oct 28Nov 12
