-
Notifications
You must be signed in to change notification settings - Fork 101
Pull requests: google-ai-edge/LiteRT-LM
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Use TensorBuffer::Clear() instead of ZeroTensorBuffer()
#1280
opened Jan 25, 2026 by
copybara-service
bot
Loading…
Reverts 374f764e2010020599680c28ae4773805e9b8138
#1276
opened Jan 24, 2026 by
copybara-service
bot
Loading…
Add constrained decoding to Conversation API, enabling support for external constraints and LLGuidance.
#1275
opened Jan 24, 2026 by
copybara-service
bot
Loading…
Fix local_xla reference and drop python 3.9 support.
#1273
opened Jan 23, 2026 by
copybara-service
bot
Loading…
Updated the RunTextScoring functions to return both aggregated score and per-token scores.
#1272
opened Jan 23, 2026 by
copybara-service
bot
Loading…
Remove precision deduction in delegate kernel.
#1228
opened Jan 15, 2026 by
copybara-service
bot
Loading…
llm model proto changed, adding a new gemma model.
#1222
opened Jan 14, 2026 by
copybara-service
bot
Loading…
Add the KVCacheCopier with CPU implementation
#1219
opened Jan 13, 2026 by
copybara-service
bot
Loading…
[litertlm] de-duplicate ConversationConfig::Create*
#1204
opened Jan 10, 2026 by
copybara-service
bot
Loading…
Minor clean up to LiteRT LM's compiler logs
#1200
opened Jan 9, 2026 by
copybara-service
bot
Loading…
Support running the model multiple times #2.5
#1187
opened Jan 7, 2026 by
copybara-service
bot
Loading…
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.