8000 llama : rework embeddings logic by ggerganov · Pull Request #14208 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

llama : rework embeddings logic #14208

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 6 commits into from
Jun 16, 2025
Merged

llama : rework embeddings logic #14208

merged 6 commits into from
Jun 16, 2025

Conversation

ggerganov
Copy link
Member
@ggerganov ggerganov commented Jun 16, 2025 •
edited
Loading

fix #14204

  • Support embeddings with causal attention
  • Support logits + embeddings output
  • llama-server requires --embeddings flag to compute embeddings/reranking
  • Auto-fill embedding batches with output[i] == true when batch.logits == NULL

@ggerganov ggerganov mentioned this pull request Jun 16, 2025
Closed
@ggerganov ggerganov marked this pull request as ready for review June 16, 2025 09:30
@ggerganov ggerganov requested a review from ngxson as a code owner June 16, 2025 09:30
@ggerganov ggerganov merged commit d3e64b9 into master Jun 16, 2025
55 checks passed
@ggerganov ggerganov deleted the gg/llama-rework-embeddings branch June 16, 2025 11:14
@ggerganov ggerganov mentioned this pull request Jun 16, 2025
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@ngxson ngxson Awaiting requested review from ngxson ngxson is a code owner

Assignees
No one assigned
Labels
examples server
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Eval bug: Error in trying to use llama-server with Qwen3-Embedding-0.6B-GGUF
1 participant
@ggerganov
0