Jesse Gross a807985e59 ggml: Check for OOM and return as Go errors ...

If there is a CUDA OOM, we currently don't check the return value
and will evetually segfault. This checks for the problem and generates
a Go error. At the moment, this will still result in a panic but having
the error is the first step to being able to handle it more gracefully.

2025-04-08 10:01:28 -07:00

..

backend

ggml: Check for OOM and return as Go errors

2025-04-08 10:01:28 -07:00

nn

attention: Remove unnecessary contiguous operations

2025-03-01 20:53:23 -08:00

backend.go

model: support for mistral-small in the ollama runner

2025-04-03 16:57:36 -07:00