-
Notifications
You must be signed in to change notification settings - Fork 160
Pull requests: google-ai-edge/LiteRT
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Fix gcc 9.4 build. (__has_builtin was introduced in gcc 10)
#5080
opened Dec 25, 2025 by
copybara-service
bot
Loading…
Add LeakyRelu support to MTK compiler plugin
#5076
opened Dec 24, 2025 by
copybara-service
bot
Loading…
PR #5019: Use OpenVINO level zero remote tensor as LiteRT custom buffer
#5075
opened Dec 24, 2025 by
copybara-service
bot
Loading…
Initialize xnn before checking fingerprint.
#5074
opened Dec 24, 2025 by
copybara-service
bot
Loading…
Qualcomm AI Engine Direct - Add feature to skip op with ids.
#5073
opened Dec 24, 2025 by
ChunHsuehLee
•
Draft
Mark stablehlo.scatter and stablehlo.reduce_window as unsupported
#5063
opened Dec 23, 2025 by
copybara-service
bot
Loading…
Bump XNNPACK version for open source builds.
#5061
opened Dec 23, 2025 by
copybara-service
bot
Loading…
Integrate the refactored litert_plugin_compiler in-place of compiler_api_wrapper artifacts.
#5058
opened Dec 22, 2025 by
copybara-service
bot
Loading…
This corrects a numerical precision issue identified in several TFLite reference kernels. The issue stems from a "narrowing" effect where intermediate variables intended for double precision calculations were being evaluated in float precision due to the placement of type casts.
#5047
opened Dec 19, 2025 by
copybara-service
bot
Loading…
Use the XNNPack packing fingerprints to invalidate the weight cache.
#5045
opened Dec 19, 2025 by
copybara-service
bot
Loading…
Previous Next
ProTip!
no:milestone will show everything without a milestone.