Jeffrey Morgan a937a68317 server: fix slow 'ollama rm' of models with many layers (#13680) ...

RemoveLayers was calling Manifests() for each layer to check if it was
shared with other models. For models with many blobs (e.g., tensor
models), this caused O(N*M) manifest reads.

Now loads manifests once and builds a set of in-use digests.

2026-01-12 13:17:48 -08:00

3.8 KiB

Raw Permalink Blame History

View Raw