is the model support TGI?
#152
by
AminSharif
- opened
i have served the model using transformers serve command on 2 RTX 3080 ti with 12GB VRAM for each one and i have latency
can i use TGI method?
i have served the model using transformers serve command on 2 RTX 3080 ti with 12GB VRAM for each one and i have latency
can i use TGI method?