Why the model config for bert is using instance group as CPU instead of GPU? - Githubissues

triton-inference-server / fastertransformer_backend

BSD 3-Clause "New" or "Revised" License

411 stars 134 forks source link

Why the model config for bert is using instance group as CPU instead of GPU? #147

Closed sfc-gh-zhwang closed 1 year ago