-
Notifications
You must be signed in to change notification settings - Fork 13k
[Gemma x Gemini CLI] Add an Experimental Gemma Router that uses a LiteRT-LM shim into the Composite Model Classifier Strategy #17231
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.
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
Merged
Merged
Changes from 20 commits
Commits
Show all changes
33 commits
Select commit
Hold shift + click to select a range
3ebe580
Add quick support for ollama and litert-lm router inference with gemm…
sidwan02 2d47336
Remove ollama router and modularize liter-lm router into new gemma cl…
sidwan02 222ae37
Simplify gemmaModelRouter experimental setting to implicitly use lite…
sidwan02 4bed6b9
Add engineered gemma classifier system prompt and reminder + router c…
sidwan02 06e8059
Flatten chat history in gemma Classifier for much better performance.
sidwan02 04aab94
In Gemma router fix TCP timeout if litert-lm shim is started but wron…
sidwan02 4dbce54
Add tests for Gemma router and LiteRT services + simplify flatten cha…
sidwan02 8e22c16
Add tests for gemma model router settings.
sidwan02 f556d5b
Remove unused ollama and reminder prompt config dependencies
sidwan02 c9f8b57
Update gemma model router classifier defaults to latest host and mode…
sidwan02 960a6f4
Clean up router logs and debug chat history file
sidwan02 393b266
Simplify local gemini client API call to litert-lm shim
sidwan02 3d5ab14
Simplify gemma response cleaning with jsonrepair
sidwan02 13ee548
gemma router invalid/undownloaded model is handled by the litert-lm s…
sidwan02 3b32f57
Delete temp dev files and fix gitignore
sidwan02 4b06d45
fix incorrect call to resolveClassifierModel in gemma classifier stra…
sidwan02 9edc0a1
npm preflight passing, setting and docs updated
sidwan02 1a58a29
remove skills and gemma model router from default settings json
sidwan02 80e96f7
rename localGeminiClient to localLiteRtLmClient
sidwan02 8aec362
Defaults for gemma model router are not re-checked in the litert lm c…
sidwan02 651471e
Lazily initialize litertlm client and reuse in new calls to gemma router
sidwan02 ba64940
Remove prompt duplication between gemma3:1b system prompt and reminder
sidwan02 41333cb
gemma classifier prompt filters out non text parts
sidwan02 9810bdb
Propagate abort signal to litertlm client in gemma classifier
sidwan02 e38f5a1
Retire jsonrepair in client (shim handles this) + add comment explain…
sidwan02 6c9e650
Update tests for gemmaClassifierStrategy and localLiteRtLmClient to h…
sidwan02 b1d8834
Update gemma router documentation with requirements and alerts
sidwan02 6d48b06
Only allow gemma3-1b-gpu-custom to be set for gemma model router.
sidwan02 fca16d8
Reset package-lock.json and vitest.config.ts
sidwan02 a98e133
Merge branch 'synced' into gemma-router-pr
sidwan02 c7a0b7e
Final test fixes with preflight
sidwan02 1e85554
Merge branch 'main' into gemma-router-pr
sidwan02 7ab16b7
Merge branch 'main' into gemma-router-pr
allenhutchison File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
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
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
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
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
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
Oops, something went wrong.
Oops, something went wrong.
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.
Uh oh!
There was an error while loading. Please reload this page.