nicole pardal 3475d915cb embeddings: modified batch size (#13429) ...

This PR detects embedding models and sets batch_size = context_size so the full input fits in a single batch.
Previously, if batch size was smaller than the input, tokens could be split across batches and cause a SIGTRAP crash.
This change ensures all tokens stay in one batch and prevents crashes.
Fixes: #12938 #13054

Co-authored-by: Jesse Gross <jesse@ollama.com>

2025-12-11 15:36:31 -08:00

54 KiB

Raw Blame History

View Raw