Wang, Yi
Wang, Yi
inference performance | perf | A100 | Gaudi2 | |-------|------|----------| | duration | 1x| 0.58x|
@jiminha please review the perf data and ci testcase
some model like https://huggingface.co/ise-uiuc/Magicoder-S-CL-7B only has safetensors
@delock @tjruwase please help review
should work with https://github.com/huggingface/transformers/pull/22196
@microsoft-github-policy-service agree [company="intel"]
@microsoft-github-policy-service agree company=intel
@delock @yao-matrix
@RezaYazdaniAminabadi @jeffra @mrwyattii @awan-10 @cmikeh2 @arashb please help review. thanks