fix model_free saving with single shard and MXFP fake format evaluation #2391
fix: correct device mapping in run_model_evaluation function
1ee6556b
feat: implement optimized RTN toggle for NVFP4 E5M3 quantization and …
7d204be9
feat: update model-free compressor to preserve activation config and …
0d240340
update per comments
ba29bf9a
xin3he
added this to the 0.16.0 milestone 15 days ago
n1ck-guo
approved these changes
on 2026-09-21
xin3he
merged
f4d2c162
into main 14 days ago
xin3he
deleted the xinhe/9-20a branch 14 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub