345420998e
In mult-brand GPU setups, if we couldn't fully load the model we would fall through the scheduler and mistakenly try to load across a mix of brands. This makes sure we find the set of GPU(s) that best fit for the partial load. |
||
|---|---|---|
| .. | ||
| testdata/tools | ||
| auth.go | ||
| download.go | ||
| fixblobs.go | ||
| fixblobs_test.go | ||
| images.go | ||
| layer.go | ||
| manifest.go | ||
| manifest_test.go | ||
| model.go | ||
| model_test.go | ||
| modelpath.go | ||
| modelpath_test.go | ||
| prompt.go | ||
| prompt_test.go | ||
| routes.go | ||
| routes_create_test.go | ||
| routes_delete_test.go | ||
| routes_generate_test.go | ||
| routes_list_test.go | ||
| routes_test.go | ||
| sched.go | ||
| sched_test.go | ||
| upload.go | ||