This repository has been archived by the owner on Oct 25, 2024. It is now read-only.
Unify the woq config weight_dtype for int4 and fp4 on different devices #4984
PenghuiChengchatbot-test.yml
on: pull_request
call-inference-llama-2-7b-chat-hf
/
inference test
3m 6s
call-inference-mpt-7b-chat
/
inference test
2m 57s