Repository navigation
Add EmbeddingGemma 2 text encoder support to gemma.cpp. - #1082
Open
copybara-service[bot] wants to merge 1 commit into
Open
copybara-service[bot] wants to merge 1 commit into
copybara-service[bot] wants to merge 1 commit into
Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
copybara-service
Bot
force-pushed
the
test_1018187738
branch
from
November 10, 2026 20:08
2146a4c to
4d776c6
Compare
Embedding inference in gemma.cpp previously lacked open-weights model configurations, table-less per-layer embeddings (PLE), and Safetensors checkpoint conversion. Add `Model::EMBEDDING_GEMMA2_LM` (24-layer 5:1 local/global bidirectional attention, table-less PLE, and a 768D Matryoshka projection head), expose `Gemma::ComputeEmbedding`, `Gemma::ComputeEmbeddings`, `EmbeddingsWorkspace`, and `--embed_dim` in the public C++ API and CLI, enable batched PLE in `ComputeEmbeddings`, and extend `convert_from_safetensors.py` to export `embeddinggemma2-lm-*` checkpoints. PiperOrigin-RevId: 1018187738
copybara-service
Bot
force-pushed
the
test_1018187738
branch
from
November 10, 2026 22:41
4d776c6 to
1f4e800
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add EmbeddingGemma 2 text encoder support to gemma.cpp.
Embedding inference in gemma.cpp previously lacked open-weights model configurations, table-less per-layer embeddings (PLE), and Safetensors checkpoint conversion.
Add
Model::EMBEDDING_GEMMA2_LM(24-layer 5:1 local/global bidirectional attention, table-less PLE, and a 768D Matryoshka projection head), exposeGemma::ComputeEmbedding,Gemma::ComputeEmbeddings,EmbeddingsWorkspace, and--embed_dimin the public C++ API and CLI, enable batched PLE inComputeEmbeddings, and extendconvert_from_safetensors.pyto exportembeddinggemma2-lm-*checkpoints.