Skip to content

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

New pull request New
74 Open 564 Closed
74 Open 564 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

Fix JAX bridge incompatibility with NumPy < 2.0
#840 opened Oct 24, 2025 by copybara-service bot Loading…
Add EmbeddingGemma-300M example to AI Edge Torch.
#832 opened Oct 8, 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 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…
Cast all i64 tensor to i32, and f64 to f32.
#803 opened Sep 4, 2025 by copybara-service bot Loading…
Remove reference to an internal file.
#788 opened Aug 13, 2025 by copybara-service bot Loading…
Add jax lowering to cast f64 to f32 for aten ops add, sub, lt, mul, where.
#786 opened Aug 12, 2025 by copybara-service bot Loading…
Add jax lowering to cast f64 to f32 for aten ops add, sub, lt, mul, where.
#785 opened Aug 12, 2025 by copybara-service bot Loading…
Add TPU inference pipeline for SmolVLM2.
#784 opened Aug 11, 2025 by copybara-service bot Loading…
Add aten.scatter.src gpu friendly decomp
#779 opened Aug 8, 2025 by copybara-service bot Loading…
Fix harden checkpoint loading and LoRA initialization issue ci:run status:awaiting review Awaiting PR review
#778 opened Aug 7, 2025 by gaikwadrahul8 Loading…
Add jax lowering to cast f64 to f32 for aten ops add, sub, lt, mul, where.
#774 opened Aug 6, 2025 by copybara-service bot Loading…
Add a flag "cast_i64_inputs_to_i32" to cast all i64 tensor to i32.
#773 opened Aug 5, 2025 by copybara-service bot Loading…
Add numeric verification for the SmolVLM2 Image Encoder Model.
#771 opened Aug 3, 2025 by copybara-service bot Loading…
Support dynamic shape in transformers_integration/export_util.py.
#770 opened Jul 31, 2025 by copybara-service bot Loading…
Add torch_tfl topk lowerings
#769 opened Jul 31, 2025 by copybara-service bot Loading…
Update optimization barrier output to match the input structure.
#768 opened Jul 30, 2025 by copybara-service bot Loading…
Update optimization barrier output to match the input structure.
#766 opened Jul 30, 2025 by copybara-service bot Loading…
Add optimization barrier after embedding lookup layer (after the reshape back to [bsz, seq_len, ...]).
#762 opened Jul 29, 2025 by copybara-service bot Loading…
Update optimization barrier output to match the input structure.
#761 opened Jul 29, 2025 by copybara-service bot Loading…
Internal access modifications.
#760 opened Jul 28, 2025 by copybara-service bot Loading…
ProTip! Adding no:label will show everything without a label.