FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

fix: handle embedding models without KV memory by abetlen · Pull Request #2160 · abetlen/llama-cpp-python · GitHub

/ llama-cpp-python Public

fix: handle embedding models without KV memory - #2160

Merged
abetlen merged 2 commits into
mainfrom
abetlen/fix-embedding-null-memory
Mar 25, 2026
ConversationCommits (2)ChecksFiles changed
Merged

fix: handle embedding models without KV memory#2160
abetlen merged 2 commits into
mainfrom
abetlen/fix-embedding-null-memory

Conversation

abetlen commented Mar 25, 2026 •
edited
Loading

Copy link
Copy Markdown
Owner
  • make LlamaContext.kv_cache_clear() a no-op when upstream context has no memory object (encoder-only embedding models without a kv cache)
  • switch the embedding smoke test to an encoder embedding model: CompendiumLabs/bge-small-en-v1.5-gguf (bge-small-en-v1.5-q4_k_m.gguf) to catch these issues more quickly in the future

Closes #2159.

abetlen merged commit ac59e5a into main Mar 25, 2026
abetlen deleted the abetlen/fix-embedding-null-memory branch March 25, 2026 22:04
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

Error with latest version of llama-cpp-python 0.3.18 and vector embedding

1 participant

Back | FazBrowse Home | New Git URL