[OpenVINO] Add workaround logic for default int4 quantization of openai/gpt-oss-20b model #1490
Add a workaround for GPT-OSS quantization
db811bd0
Fix tests
610e33ca
Add exception
a14f7ec6
Address review comments
fb08c2ad
Add config save/load tests
8081d811
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub