context : allow cache-less context for embeddings #13108
Draft
+2,038
−1,067
Conversation
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
ggml-ci
ggml-ci
ggml-ci
ggml-ci
8 tasks
ggerganov
force-pushed
the
gg/llama-kv-cache-v6
branch
5 times, most recently
from
58115a2 to
7e79a42
Compare
|
I'll work on rebasing and merging this next - it should be a good improvement for embedding models by reducing the allocated memory during inference. |
Green-Sky
reviewed
May 2, 2025
| @@ -49,7 +49,7 @@ static void batch_decode(llama_context * ctx, llama_batch & batch, float * outpu | |||
| } | |||
| } else if (!llama_model_has_encoder(model) && llama_model_has_decoder(model)) { | |||
| // decoder-only model | |||
| if (llama_decode(ctx, batch) < 0) { | |||
| if (llama_encode(ctx, batch) < 0) { | |||
There was a problem hiding this comment.
Not yet, needs a bit of work.
One of the main changes in this PR is that we will start using llama_encode() when computing embeddings and this change is part of the tests that I did.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
target #12799
There is no need to create a KV cache when using embeddings-only models such as BERT.