mirror of https://github.com/ollama/ollama
3475d915cb
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> |
||
|---|---|---|
| .. | ||
| llm_darwin.go | ||
| llm_linux.go | ||
| llm_windows.go | ||
| server.go | ||
| server_test.go | ||
| status.go | ||