Inference Node — runs on each GPU machine, cuBLAS SGEMM via Panama FFI, pipeline forward pass, gRPC activation transfer
Version0.1.1compared with

Version Details

Compile Changes (5)

0.1.0 0.1.1
ChangeGroup / ArtifactPreviousCurrent
~ Updated cab.ml » api0.1.00.1.1
~ Updated cab.ml » health0.1.00.1.1
~ Updated cab.ml » kvcache0.1.00.1.1
~ Updated cab.ml » lora0.1.00.1.1
~ Updated cab.ml » registry0.1.00.1.1