Open MLHafizur opened 1 year ago
I found a couple issues in the gRPC repo that look relevant:
From the later comments on the second issue it sounds like it could be related to a client side disconnect during process of a gRPC request with the new AsyncIO API.
@MLHafizur this might indicate that the MM and/or adapter containers restarted, could you check whether that's the case?
We have deployed models using MLServer Custom Runtime. Getting the following error during inferencing:
Never seen this error before, any idea?