Failed to deploy the model in inference endpoint with NO error
#25
by
Isgservices-builderai
- opened
Same result Nvidia L4 · 4x GPU · 96 GB
Have tried to create an inference point for this model couple of time and it failed on all occasions without any error. Here is the snippet of my log:
What could be the issue? I'm using Nvidia A100 - 2xGPU.160GB. Have increased Max Number of Tokens to 8K.
I got Bin12345/AutoCoder running