Skip to content

Pull requests: apple/coremltools

New pull request New
58 Open 1,055 Closed
58 Open 1,055 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 log_softmax fp16 underflow and logcumsumexp fp16 overflow on ANE via stable decomposition
#2727 opened May 29, 2026 by Ashutosh0x Loading…
2
Fix logsumexp fp16 overflow on ANE via stable max-shift decomposition
#2726 opened May 29, 2026 by Ashutosh0x Loading…
1
Fix softplus and mish fp16 overflow on ANE via stable decomposition
#2725 opened May 28, 2026 by Ashutosh0x Loading…
2
Accumulate activation calibration ranges
#2724 opened May 28, 2026 by kiwigitops Loading…
1
Fix max_pool conversion for unbatched torch input
#2723 opened May 26, 2026 by devin-lai Loading…
1
Fix bisect_model pytest dependency
#2722 opened May 25, 2026 by kiwigitops Loading…
1
Support real-valued input in torch.fft.irfft converter
#2721 opened May 25, 2026 by adityasingh2400 Loading…
1
Raise NotImplementedError for unsupported TF symmetric pad mode
#2720 opened May 25, 2026 by adityasingh2400 Loading…
1
Fix matmul type_inference for 1-D inputs
#2719 opened May 25, 2026 by adityasingh2400 Loading…
1
Fix torch var/std converter ignoring correction > 1 under tracing
#2718 opened May 25, 2026 by adityasingh2400 Loading…
Support return_indices for max_pool2d in the torch frontend
#2717 opened May 24, 2026 by adityasingh2400 Loading…
1
Add torch.tensor_split op support for PyTorch frontend
#2715 opened May 24, 2026 by eyupcanakman Contributor Loading…
1 task done
1
1
Reject stateful programs whose output aliases a state-write source
#2713 opened May 22, 2026 by john-rocky Contributor Loading…
Fix Conv3d w8a8 quantization rank mismatch
#2712 opened May 21, 2026 by tritolol Contributor Loading…
2 tasks
1
2
Cast torch.multinomial output to int to match torch's int64 contract (fixes #2337)
#2710 opened May 20, 2026 by LeSingh1 Contributor Loading…
1
Reshape per-channel ImageType.scale to broadcast over channel-first input (fixes #2461)
#2709 opened May 20, 2026 by LeSingh1 Contributor Loading…
1
Fix broken Min/Max Tracking Across Calibration Batches
#2705 opened May 18, 2026 by Ebraheem1 Loading…
1
7
Register __ior__ as alias of bitwise_or (fixes #2584)
#2702 opened May 18, 2026 by LeSingh1 Contributor Loading…
1
7
Raise NotImplementedError at conversion time for reflect/replicate pad >2D (fixes #2576, #2571)
#2701 opened May 18, 2026 by LeSingh1 Contributor Loading…
2
7
Fix ReplicationPad3d failing at CoreML ML Program runtime
#2697 opened May 14, 2026 by tritolol Contributor Loading…
1
3
Add Python 3.14 support to pip wheels
#2696 opened May 12, 2026 by KOTHA-SRIVIBHU Loading…
1
Fix palettize_weights enable_per_channel_scale=True crashing MPSGraph on Apple Neural Engine (macOS 26)
#2688 opened May 3, 2026 by john-rocky Contributor Loading…
4 tasks done
Convert auto-regressive LLMs with prefill/decode multifunctions (docs-guide)
#2686 opened May 1, 2026 by john-rocky Contributor Loading…
1 of 2 tasks
Raise a clear error when a no-input model targets below iOS18
#2684 opened May 1, 2026 by john-rocky Contributor Loading…
1 task done
1
5
Cast int input to fp32 in torch reciprocal converter
#2683 opened May 1, 2026 by john-rocky Contributor Loading…
2 tasks done
1
1
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.