[PR #4399] fix embedding by adding fixes from llama.cpp upstream #11476

Closed
opened 2026-04-12 23:30:55 -05:00 by GiteaMirror · 0 comments
Owner

Original Pull Request: https://github.com/ollama/ollama/pull/4399

State: closed
Merged: No


Embedding appears broken since v0.1.32

See #3777 #4207 for details.

This PR applies fixes based on 1b67731e18 (diff-87355a1a297a9f0fdc86af5e2a59cae153290f58d68822cd10c30fee4f7f7076).

I've tested it and embedding vectors looks correct after applying this patch.

**Original Pull Request:** https://github.com/ollama/ollama/pull/4399 **State:** closed **Merged:** No --- Embedding appears broken since v0.1.32 See #3777 #4207 for details. This PR applies fixes based on https://github.com/ggerganov/llama.cpp/commit/1b67731e184e27a465b8c5476061294a4af668ea#diff-87355a1a297a9f0fdc86af5e2a59cae153290f58d68822cd10c30fee4f7f7076. I've tested it and embedding vectors looks correct after applying this patch.
GiteaMirror added the pull-request label 2026-04-12 23:30:55 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#11476