Skip to content

Pull requests: google-ai-edge/litert-torch

New pull request New
87 Open 705 Closed
87 Open 705 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

OS NPU calibrate pipeline.
#1033 opened May 21, 2026 by copybara-service Bot Loading…
Fail fast on dynamic_shapes and guard arange rewrite for symbolic args
#1024 opened May 13, 2026 by pctablet505 • Draft
Preserve dict keys in flat_arg_names for positional args
#1023 opened May 13, 2026 by pctablet505 Loading…
1
Internal only change
#1021 opened May 8, 2026 by copybara-service Bot Loading…
Internal only change
#1016 opened May 6, 2026 by copybara-service Bot Loading…
Allows to test on MacOS in GitHub workflows.
#1011 opened Apr 30, 2026 by copybara-service Bot Loading…
Change the OpQuantizationRecipe's operation: TFLOperationName field to operators: set[TFLOperationName].
#1009 opened Apr 28, 2026 by copybara-service Bot Loading…
Internal only change
#1007 opened Apr 27, 2026 by copybara-service Bot Loading…
Update litert_torch/generative/README.md with unified model format and bundling instructions.
#991 opened Mar 31, 2026 by copybara-service Bot Loading…
Optimize Flatbuffer export for numeric DenseElementsAttr and DenseResourceElementsAttr.
#952 opened Feb 18, 2026 by copybara-service Bot Loading…
Fix Gemma3 examples
#932 opened Feb 8, 2026 by Christian24 Loading…
Add final L2 normalization option and update README for Embedding Gemma-300M
#931 opened Feb 7, 2026 by kamalkraj Loading…
Updating the Gemma3 verification script to support safetensors checkpoints and numerical verification for FunctionGemma, a variant of Gemma3 270m.
#927 opened Feb 4, 2026 by copybara-service Bot Loading…
Use standard PyTorch decomposition for upsample_nearest2d.
#878 opened Jan 9, 2026 by copybara-service Bot Loading…
Add test cases to convert CONV_2D ops.
#857 opened Nov 20, 2025 by copybara-service Bot Loading…
Relax the check to enable Pad+Conv fusion with RELU6 to avoid numeric diffs in FP16.
#856 opened Nov 19, 2025 by copybara-service Bot Loading…
Internal only changes
#855 opened Nov 19, 2025 by copybara-service Bot Loading…
Fix JAX lowerings to align with torch_xla2 update.
#845 opened Nov 3, 2025 by copybara-service Bot Loading…
Fix JAX bridge incompatibility with NumPy < 2.0
#840 opened Oct 24, 2025 by copybara-service Bot Loading…
Refactor blockwise quantization granularity.
#828 opened Oct 2, 2025 by copybara-service Bot Loading…
Add EmbeddingGemma to generative
#824 opened Sep 28, 2025 by copybara-service Bot Loading…
Enable topk and scatter_nd conversion via tfl ops.
#814 opened Sep 15, 2025 by copybara-service Bot Loading…
Add litert dialects for tfl ops.
#812 opened Sep 12, 2025 by copybara-service Bot Loading…
Update assignee for issue auto-assignment ci:run CLA:yes status:awaiting review Awaiting PR review
#810 opened Sep 11, 2025 by gaikwadrahul8 Loading…
Automated Code Change
#804 opened Sep 8, 2025 by copybara-service Bot Loading…
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.