-
Notifications
You must be signed in to change notification settings - Fork 621
Pull requests: google-ai-edge/LiteRT-LM
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat(python): add PromptTemplate API across C API and Python bindings
#2792
opened Jul 9, 2026 by
copybara-service
Bot
Loading…
Guard HuggingFaceTokenizer with a build flag
#2791
opened Jul 9, 2026 by
copybara-service
Bot
Loading…
[litertlm] Add constrained decoding / response format API in Python
#2789
opened Jul 9, 2026 by
copybara-service
Bot
Loading…
feat(c): add litert_lm_get_last_error_message C API for thread-local error string retrieval
#2785
opened Jul 9, 2026 by
copybara-service
Bot
Loading…
NPU: Initial implementation for sliding window attention support in HW cache update
#2784
opened Jul 9, 2026 by
copybara-service
Bot
Loading…
Allow configurable NPU KV cache initialization value via model metadata.
#2776
opened Jul 9, 2026 by
copybara-service
Bot
Loading…
feat(kotlin): add maxOutputToken API to ConversationConfig and sendMessage
#2771
opened Jul 8, 2026 by
copybara-service
Bot
Loading…
Update litert_lm_api Linux build config and METADATA presubmits
#2767
opened Jul 8, 2026 by
copybara-service
Bot
Loading…
ci(win): conditionally download model and run pytest when RUN_PYTEST is true
#2747
opened Jul 7, 2026 by
copybara-service
Bot
Loading…
Enable sampler-handled decode input for models with in-graph embeddings
#2744
opened Jul 7, 2026 by
john-rocky
Loading…
Previous Next
ProTip!
Follow long discussions with comments:>50.