Skip to content

Pull requests: apple/coremltools

New pull request New
40 Open 1,042 Closed
40 Open 1,042 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

Convert auto-regressive LLMs with prefill/decode multifunctions (docs-guide)
#2686 opened May 1, 2026 by john-rocky Contributor Loading…
1 of 2 tasks
Replace getattr with constant when buffer is a graph output
#2685 opened May 1, 2026 by john-rocky Contributor Loading…
3 tasks done
1
Auto-bump spec version to iOS18 for models with no inputs
#2684 opened May 1, 2026 by john-rocky Contributor Loading…
3 tasks done
1
Cast int input to fp32 in torch reciprocal converter
#2683 opened May 1, 2026 by john-rocky Contributor Loading…
2 tasks done
1
Return a 1-D vector from torch.diagonal converter
#2682 opened May 1, 2026 by john-rocky Contributor Loading…
2 tasks done
1
Preserve input dtype in torch floor_divide converter
#2681 opened May 1, 2026 by john-rocky Contributor Loading…
2 tasks done
1
Apply alpha scale factor in torch add/sub converters
#2680 opened May 1, 2026 by john-rocky Contributor Loading…
3 tasks done
1
Fix ImageType handling in _gen_random_feature_value
#2679 opened Apr 30, 2026 by sisaman Loading…
1
Add normalize_affine_dequantize_int8 pass to fix GPU inference for pregenerated linear_symmetric models
#2677 opened Apr 28, 2026 by wangpengmit Loading…
1
Re-encode linear_symmetric int8 weights as uint8 in constexpr_affine_dequantize
#2675 opened Apr 25, 2026 by wangpengmit Loading…
2
Add regression test for length-1 tensor int casts
#2662 opened Mar 16, 2026 by hayeah Loading…
1
Update XGBoost max supported version to 3.0.2
#2657 opened Mar 5, 2026 by sid22669 Contributor Loading…
2 tasks done
1
6
Fix excessive memory allocation for static-shape attention ops
#2636 opened Dec 30, 2025 by Pranaykarvi Contributor Loading…
1
13
Reduce mish error by an alternative without softplus op
#2618 opened Nov 7, 2025 by ChinChangYang Contributor Loading…
30
fix type hints in OptimizationConfig
#2613 opened Oct 27, 2025 by catwell Loading…
chore: ANE can now do 2gb
#2593 opened Sep 10, 2025 by FL33TW00D Contributor Loading…
1
**Fix reciprocal op crash on int32 input by raising ValueError (Fixes #2579)**
#2580 opened Aug 5, 2025 by Pranaykarvi Contributor Loading…
1
5
Add split copy
#2563 opened Jul 28, 2025 by metascroy Contributor Loading…
3
Fix immediate output getattr
#2541 opened Jun 12, 2025 by tritolol Contributor Loading…
1
5
Fix the aten power tensor offload issue
#2457 opened Feb 25, 2025 by billmguo Contributor Loading…
1
R** move cmake installation into env_create.sh
#2393 opened Nov 13, 2024 by guru-desh Contributor Loading…
9
Skip casting model inputs to fp32 if weights and inputs are all fp16
#2274 opened Jul 11, 2024 by jeethu Loading…
3
Clarifying the default function name field for multifunction in the docs
#2246 opened Jun 18, 2024 by DawerG Collaborator Loading…
1
Kwargs propagation from _get_model in quantize_weights to MLModel in _get_model
#2244 opened Jun 18, 2024 by asafl Loading…
1
Update test.pip compatible with Python 3.12
#2161 opened Mar 6, 2024 by johnnynunez Loading…
13
ProTip! Filter pull requests by the default branch with base:main.