-
Notifications
You must be signed in to change notification settings - Fork 415
Pull requests: google-ai-edge/LiteRT
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[ir-model] Various support / convert function fixes
#9211
opened Aug 11, 2026 by
copybara-service
Bot
Loading…
Add GPU shader serialization options to benchmark_model
#9207
opened Aug 10, 2026 by
copybara-service
Bot
Loading…
Calibrate ATS floating-point tolerances for half-precision accelerators.
#9205
opened Aug 10, 2026 by
copybara-service
Bot
Loading…
Add support for passing a custom GPU accelerator handle via environment options.
#9203
opened Aug 10, 2026 by
copybara-service
Bot
Loading…
Expose accelerator query APIs in LiteRT runtime C API and C++ Environment
#9202
opened Aug 10, 2026 by
copybara-service
Bot
Loading…
Add
YNN_NODE_FLAG_SYMMETRIC_B to quantized int8 weight dots
#9201
opened Aug 10, 2026 by
copybara-service
Bot
Loading…
Dynamically resolve CUDA data dir in TensorFlow MLIR lit test runner.
#9197
opened Aug 10, 2026 by
copybara-service
Bot
Loading…
PR #124016: [TFLite] Preserve Keras tracing errors on empty fallback graphs
#9196
opened Aug 10, 2026 by
copybara-service
Bot
Loading…
PR #124015: [TFLite] Clarify Interpreter input detail ordering
#9195
opened Aug 10, 2026 by
copybara-service
Bot
Loading…
[LiteRT] Improve error message for unaligned numpy arrays in Python TensorBuffer API
#9176
opened Aug 7, 2026 by
copybara-service
Bot
Loading…
Fix enclosing uncomment end in open source only section
#9166
opened Aug 6, 2026 by
copybara-service
Bot
Loading…
Implement generic op delegation filtering for YNNPACK.
#9163
opened Aug 6, 2026 by
copybara-service
Bot
Loading…
Previous Next
ProTip!
Updated in the last three days: updated:>2026-08-07.