laya-coreml 0.1.0__tar.gz

laya_coreml-0.1.0/.gitignore

@@ -0,0 +1,17 @@
+.venv/
+.upstream/
+__pycache__/
+.pytest_cache/
+.ruff_cache/
+models/
+artifacts/
+*.mlpackage/
+*.mlmodelc/
+*.trace/
+*.safetensors
+*.pt
+*.log
+dist/
+build/
+.DS_Store
+.env

laya_coreml-0.1.0/LICENSE

@@ -0,0 +1,176 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

laya_coreml-0.1.0/NOTICE

@@ -0,0 +1,22 @@
+laya-coreml
+Copyright 2026 laya-coreml contributors
+
+This product includes software adapted from Laya (Apache-2.0):
+https://github.com/NandhaKishorM/laya
+Copyright Convai Innovations and Laya contributors.
+Upstream source revision: 6a5819129eb220570792e417e49723d697efd76f
+
+Prompt construction, tokenization, result formatting, validation fixtures,
+the ModernBERT architecture implementation, and the Snake game, policy, terminal
+UI, recording/export and benchmark tools are adapted from laya-mlx:
+https://github.com/mizorewww/laya-mlx
+Copyright 2026 laya-mlx contributors. Licensed under Apache-2.0.
+Adapted revision: fc1df62828a3fedf4d8229fdac1cbd85f1cdf337
+Changes: Core ML runtime, export-only PyTorch graph, fixed/ranged shape input
+handling, Core ML validation, device planning, and performance measurement;
+ANE graph/runtime, portable model bundles and offline Core ML Snake integration.
+
+The model follows Laya's DecisionModel and Hugging Face Transformers ModernBERT.
+Original checkpoint weights belong to their respective upstream authors and
+are downloaded separately. No weights are included in this repository.
+This is an independent project, not an official Convai Innovations or Apple release.

laya_coreml-0.1.0/PKG-INFO

@@ -0,0 +1,198 @@
+Metadata-Version: 2.4
+Name: laya-coreml
+Version: 0.1.0
+Summary: Local Laya typed decisions on Apple Core ML and Neural Engine, with a live Snake demo
+Project-URL: Repository, https://github.com/mizorewww/laya-coreml
+Project-URL: Upstream, https://github.com/NandhaKishorM/laya
+Project-URL: Documentation, https://github.com/mizorewww/laya-coreml#readme
+Project-URL: Issues, https://github.com/mizorewww/laya-coreml/issues
+Project-URL: Benchmarks, https://github.com/mizorewww/laya-coreml/blob/main/docs/ANE_BENCHMARKS.md
+License-Expression: Apache-2.0
+License-File: LICENSE
+License-File: NOTICE
+Keywords: apple-silicon,coreml,decision-model,laya,local-ai,neural-engine
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: MacOS
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: <3.14,>=3.11
+Requires-Dist: coremltools<10,>=9
+Requires-Dist: huggingface-hub<2,>=0.34
+Requires-Dist: numpy<2.2,>=1.26
+Requires-Dist: safetensors>=0.6
+Requires-Dist: tokenizers<1,>=0.21
+Provides-Extra: compare
+Requires-Dist: laya-mlx==0.1.0; extra == 'compare'
+Provides-Extra: convert
+Requires-Dist: safetensors>=0.6; extra == 'convert'
+Requires-Dist: torch==2.7.0; extra == 'convert'
+Provides-Extra: demo
+Requires-Dist: pillow<13,>=12; extra == 'demo'
+Requires-Dist: rich<16,>=15; extra == 'demo'
+Provides-Extra: dev
+Requires-Dist: build>=1; extra == 'dev'
+Requires-Dist: psutil>=6; extra == 'dev'
+Requires-Dist: pytest>=8; extra == 'dev'
+Requires-Dist: ruff>=0.12; extra == 'dev'
+Provides-Extra: publish
+Requires-Dist: twine<7,>=6; extra == 'publish'
+Provides-Extra: research
+Requires-Dist: kmeans1d==0.4.0; extra == 'research'
+Description-Content-Type: text/markdown
+
+![Laya Core ML playing Snake with real local model probabilities](https://raw.githubusercontent.com/mizorewww/laya-coreml/main/docs/assets/snake-demo.gif)
+
+# Laya-CoreML
+
+**Open-weight typed decisions on Apple Silicon. Core ML, Neural Engine, zero generated tokens.**
+
+[PyPI](https://pypi.org/project/laya-coreml/) · [Hugging Face weights](https://huggingface.co/aac6fef/laya-multilingual-coreml-ane) · [中文](https://github.com/mizorewww/laya-coreml/blob/main/README.zh-CN.md)
+
+A real Laya model plays Snake locally, with visible probabilities, score, length,
+latency and safety interventions. The GIF replays a recorded Core ML run at **1× speed**.
+The game uses explicit planner features and a visible cycle safety layer.
+
+The complete active Snake loop sustained **49.1–50.0 decisions/s** across three
+uncapped 600-step episodes, with zero deaths and two safety interventions.
+[Game-loop timings and paced-rate limits](https://github.com/mizorewww/laya-coreml/blob/main/docs/SNAKE_BENCHMARKS.md)
+include rendering serialization; terminal painting is excluded.
+
+**One short multilingual decision: 4.98 ms P50 / 5.31 ms P95 on M3 Max with ANE FP16.**
+The same experiment measured **2.78× better whole-system energy per decision** than
+compiled MLX FP16. A separately validated W8 palette variant reached 4.88 ms and
+3.19× energy improvement. These are single-question results, not full Snake frame
+times; the requested 10× improvement was not achieved.
+
+## Run the demo
+
+Apple Silicon · macOS 15+ · Python 3.11–3.13.
+
+```bash
+pip install 'laya-coreml[demo]'
+hf download aac6fef/laya-multilingual-coreml-ane --local-dir models/snake
+laya-coreml-snake --model ./models/snake
+```
+
+Download once, then play offline. No PyTorch, Transformers or MLX is needed for
+inference. The terminal needs 104 columns × 35 rows. Space pauses; ↑/↓ changes
+speed; R resets; Q quits. First-time Core ML initialization can take tens of seconds.
+
+[Controls, recording and video export](https://github.com/mizorewww/laya-coreml/blob/main/docs/SNAKE_DEMO.md)
+· [Measured stable decision rates](https://github.com/mizorewww/laya-coreml/blob/main/docs/SNAKE_BENCHMARKS.md)
+· [Shareable video and recording provenance](https://github.com/mizorewww/laya-coreml/blob/main/docs/LAUNCH.md)
+
+## Ask for a decision
+
+```bash
+pip install laya-coreml
+```
+
+```python
+import laya_coreml as laya
+
+agent = laya.load("aac6fef/laya-multilingual-coreml-ane")
+result = agent.predict(
+    "The customer requests a refund of a duplicate payment.",
+    {
+        "refund": {
+            "type": "noul",
+            "instructions": "Does the customer request a refund?",
+        }
+    },
+)
+print(result["answers"]["refund"])
+```
+
+Laya returns probabilities for **choice**, ordinal **score**, and boolean **noul**
+questions. There is no autoregressive decoding or generated JSON to parse. Hub
+models download before initialization; subsequent predictions stay local. Pass
+`local_files_only=True` to require an existing cache, or load a local directory.
+
+The ANE bundle has a **96-token total limit**, including question, options and
+state. Longer requests raise a capacity error. Use
+`aac6fef/laya-multilingual-coreml` for the general-purpose 1024-token model.
+[Full API, model selection and offline usage](https://github.com/mizorewww/laya-coreml/blob/main/docs/USAGE.md).
+
+## Measured on M3 Max
+
+40-core GPU, 128 GiB, macOS 27.2. One 91-token question padded to 96, including
+prompt preparation, tokenization, arrays, synchronous inference, calibration and
+formatting. Loading and warmup are excluded. MLX enables compile, prefix caching
+and shape buckets. Six alternating 20-second blocks per implementation produced
+**65,598 stable calls**.
+
+| Metric | Compiled MLX FP16 | Core ML ANE FP16 | Core ML ANE W8 |
+|---|---:|---:|---:|
+| P50 / P95 | 6.94 / 7.39 ms | **4.98 / 5.31 ms** | **4.88 / 5.23 ms** |
+| Mean system power estimate | 61.39 W | 30.75 W | 27.39 W |
+| System energy / decision | 0.4288 J | **0.1540 J** | **0.1344 J** |
+| Speed gain | 1× | **1.39×** | **1.42×** |
+| System energy gain | 1× | **2.78×** | **3.19×** |
+
+Energy uses direct SMC PSTR sensor readings, with raw samples and explicit anomaly
+rejection. This is an estimate with sensor and background-load uncertainty.
+**Speed gain × average power ratio = energy gain**; multiplying energy by speed
+again would double-count time. The W8 variant compresses weights while retaining
+FP16 compute. It is approximate, and its package-size reduction is not a speed ratio.
+
+[Speed, energy and hardware evidence](https://github.com/mizorewww/laya-coreml/blob/main/docs/ANE_BENCHMARKS.md)
+· [Raw measurements](https://github.com/mizorewww/laya-coreml/tree/main/benchmarks/results).
+
+## Available checkpoints
+
+| Hugging Face bundle | Default engine | Capacity | Purpose |
+|---|---|---:|---|
+| [Laya 421M](https://huggingface.co/aac6fef/laya-coreml) | CPU + GPU | 512 tokens | Original English model |
+| [Multilingual 322M](https://huggingface.co/aac6fef/laya-multilingual-coreml) | CPU + GPU | 1024 tokens | General multilingual decisions |
+| [Typed Decisions 421M](https://huggingface.co/aac6fef/laya-typed-decisions-coreml) | CPU + GPU | 1024 tokens | Original specialized checkpoint |
+| [Snake GPU](https://huggingface.co/aac6fef/laya-multilingual-coreml-snake) | CPU + GPU | B3 / L64 | Batches the three compact game questions |
+| [Multilingual ANE](https://huggingface.co/aac6fef/laya-multilingual-coreml-ane) | CPU + ANE | B1 / L96 | Short decisions, FP16 |
+| [Multilingual ANE W8](https://huggingface.co/aac6fef/laya-multilingual-coreml-ane-w8) | CPU + ANE | B1 / L96 | Optional approximate palette compression |
+
+Every bundle includes tokenizer/configuration, model card, provenance, checksums
+and packaging-time validation. ANE bundles also include the exact original host
+embedding/action tensors they need. No original training checkout is required.
+
+## Port fidelity and limits
+
+The three general-purpose FP16 checkpoints match upstream selected answers on
+**189/189 validation questions**. Each passes 100 repeated calls. ANE FP16 L96
+passes **59/59 fitting questions**, with maximum calibrated-probability drift
+0.002925; W8 passes the same subset with drift 0.014393 under an unchanged 0.02
+gate. Six- and four-bit experiments failed that gate and are not published weights.
+These are conversion-fidelity fixtures, not proof of general task accuracy.
+
+A separately exported FP16 ANE L1024 graph passes the complete **63/63** fixture,
+but an actual 1024-token request takes about **91.7 ms** in its serial screen.
+The short ANE result does not establish a long-context advantage. A 600-step
+paired Snake check matches **600/600 actions**, with zero deaths and zero shield
+interventions; the current ANE adapter's three sequential calls do not establish
+a consistent full-game speedup over compiled MLX.
+
+The ordinary SDPA Core ML export and the ANE graph are different implementations.
+The ordinary export defaults to CPU+GPU after unrestricted RangeDim GPU shapes
+failed local fidelity checks. Changing its device setting alone does not reproduce
+the ANE result. The ANE rewrite uses BC1L activations, 1×1 projections and per-head
+attention; its plan and a separate Instruments trace support Neural Engine work.
+CPU still handles input/output boundaries.
+
+## Documentation and reproducibility
+
+- [Install and Python/CLI API](https://github.com/mizorewww/laya-coreml/blob/main/docs/USAGE.md)
+- [Snake demo and media](https://github.com/mizorewww/laya-coreml/blob/main/docs/SNAKE_DEMO.md)
+- [Release artifacts and pinned Hub revisions](https://github.com/mizorewww/laya-coreml/blob/main/docs/RELEASE.md)
+- [General Core ML benchmarks](https://github.com/mizorewww/laya-coreml/blob/main/BENCHMARKS.md)
+- [ANE engineering experiments](https://github.com/mizorewww/laya-coreml/blob/main/docs/ANE_ENGINEERING.md)
+- [Mathematical investigation of the 10× target](https://github.com/mizorewww/laya-coreml/blob/main/docs/ANE_MATH.md)
+- [Conversion issues and supported shapes](https://github.com/mizorewww/laya-coreml/blob/main/docs/CONVERSION.md)
+
+To export yourself, install `laya-coreml[convert]` and run
+`laya-coreml convert laya-multilingual models/custom`. ANE research conversion,
+compression and benchmark scripts live in the Git checkout. The inference wheel
+contains the portable runtime and optional terminal demo.
+
+Apache-2.0. Independent port of [Laya](https://github.com/NandhaKishorM/laya), by
+Convai Innovations and contributors, building on the [MLX sibling project](https://github.com/mizorewww/laya-mlx).
+Not an official Convai Innovations or Apple release. See
+[NOTICE](https://github.com/mizorewww/laya-coreml/blob/main/NOTICE).

laya_coreml-0.1.0/README.md

@@ -0,0 +1,155 @@
+![Laya Core ML playing Snake with real local model probabilities](https://raw.githubusercontent.com/mizorewww/laya-coreml/main/docs/assets/snake-demo.gif)
+
+# Laya-CoreML
+
+**Open-weight typed decisions on Apple Silicon. Core ML, Neural Engine, zero generated tokens.**
+
+[PyPI](https://pypi.org/project/laya-coreml/) · [Hugging Face weights](https://huggingface.co/aac6fef/laya-multilingual-coreml-ane) · [中文](https://github.com/mizorewww/laya-coreml/blob/main/README.zh-CN.md)
+
+A real Laya model plays Snake locally, with visible probabilities, score, length,
+latency and safety interventions. The GIF replays a recorded Core ML run at **1× speed**.
+The game uses explicit planner features and a visible cycle safety layer.
+
+The complete active Snake loop sustained **49.1–50.0 decisions/s** across three
+uncapped 600-step episodes, with zero deaths and two safety interventions.
+[Game-loop timings and paced-rate limits](https://github.com/mizorewww/laya-coreml/blob/main/docs/SNAKE_BENCHMARKS.md)
+include rendering serialization; terminal painting is excluded.
+
+**One short multilingual decision: 4.98 ms P50 / 5.31 ms P95 on M3 Max with ANE FP16.**
+The same experiment measured **2.78× better whole-system energy per decision** than
+compiled MLX FP16. A separately validated W8 palette variant reached 4.88 ms and
+3.19× energy improvement. These are single-question results, not full Snake frame
+times; the requested 10× improvement was not achieved.
+
+## Run the demo
+
+Apple Silicon · macOS 15+ · Python 3.11–3.13.
+
+```bash
+pip install 'laya-coreml[demo]'
+hf download aac6fef/laya-multilingual-coreml-ane --local-dir models/snake
+laya-coreml-snake --model ./models/snake
+```
+
+Download once, then play offline. No PyTorch, Transformers or MLX is needed for
+inference. The terminal needs 104 columns × 35 rows. Space pauses; ↑/↓ changes
+speed; R resets; Q quits. First-time Core ML initialization can take tens of seconds.
+
+[Controls, recording and video export](https://github.com/mizorewww/laya-coreml/blob/main/docs/SNAKE_DEMO.md)
+· [Measured stable decision rates](https://github.com/mizorewww/laya-coreml/blob/main/docs/SNAKE_BENCHMARKS.md)
+· [Shareable video and recording provenance](https://github.com/mizorewww/laya-coreml/blob/main/docs/LAUNCH.md)
+
+## Ask for a decision
+
+```bash
+pip install laya-coreml
+```
+
+```python
+import laya_coreml as laya
+
+agent = laya.load("aac6fef/laya-multilingual-coreml-ane")
+result = agent.predict(
+    "The customer requests a refund of a duplicate payment.",
+    {
+        "refund": {
+            "type": "noul",
+            "instructions": "Does the customer request a refund?",
+        }
+    },
+)
+print(result["answers"]["refund"])
+```
+
+Laya returns probabilities for **choice**, ordinal **score**, and boolean **noul**
+questions. There is no autoregressive decoding or generated JSON to parse. Hub
+models download before initialization; subsequent predictions stay local. Pass
+`local_files_only=True` to require an existing cache, or load a local directory.
+
+The ANE bundle has a **96-token total limit**, including question, options and
+state. Longer requests raise a capacity error. Use
+`aac6fef/laya-multilingual-coreml` for the general-purpose 1024-token model.
+[Full API, model selection and offline usage](https://github.com/mizorewww/laya-coreml/blob/main/docs/USAGE.md).
+
+## Measured on M3 Max
+
+40-core GPU, 128 GiB, macOS 27.2. One 91-token question padded to 96, including
+prompt preparation, tokenization, arrays, synchronous inference, calibration and
+formatting. Loading and warmup are excluded. MLX enables compile, prefix caching
+and shape buckets. Six alternating 20-second blocks per implementation produced
+**65,598 stable calls**.
+
+| Metric | Compiled MLX FP16 | Core ML ANE FP16 | Core ML ANE W8 |
+|---|---:|---:|---:|
+| P50 / P95 | 6.94 / 7.39 ms | **4.98 / 5.31 ms** | **4.88 / 5.23 ms** |
+| Mean system power estimate | 61.39 W | 30.75 W | 27.39 W |
+| System energy / decision | 0.4288 J | **0.1540 J** | **0.1344 J** |
+| Speed gain | 1× | **1.39×** | **1.42×** |
+| System energy gain | 1× | **2.78×** | **3.19×** |
+
+Energy uses direct SMC PSTR sensor readings, with raw samples and explicit anomaly
+rejection. This is an estimate with sensor and background-load uncertainty.
+**Speed gain × average power ratio = energy gain**; multiplying energy by speed
+again would double-count time. The W8 variant compresses weights while retaining
+FP16 compute. It is approximate, and its package-size reduction is not a speed ratio.
+
+[Speed, energy and hardware evidence](https://github.com/mizorewww/laya-coreml/blob/main/docs/ANE_BENCHMARKS.md)
+· [Raw measurements](https://github.com/mizorewww/laya-coreml/tree/main/benchmarks/results).
+
+## Available checkpoints
+
+| Hugging Face bundle | Default engine | Capacity | Purpose |
+|---|---|---:|---|
+| [Laya 421M](https://huggingface.co/aac6fef/laya-coreml) | CPU + GPU | 512 tokens | Original English model |
+| [Multilingual 322M](https://huggingface.co/aac6fef/laya-multilingual-coreml) | CPU + GPU | 1024 tokens | General multilingual decisions |
+| [Typed Decisions 421M](https://huggingface.co/aac6fef/laya-typed-decisions-coreml) | CPU + GPU | 1024 tokens | Original specialized checkpoint |
+| [Snake GPU](https://huggingface.co/aac6fef/laya-multilingual-coreml-snake) | CPU + GPU | B3 / L64 | Batches the three compact game questions |
+| [Multilingual ANE](https://huggingface.co/aac6fef/laya-multilingual-coreml-ane) | CPU + ANE | B1 / L96 | Short decisions, FP16 |
+| [Multilingual ANE W8](https://huggingface.co/aac6fef/laya-multilingual-coreml-ane-w8) | CPU + ANE | B1 / L96 | Optional approximate palette compression |
+
+Every bundle includes tokenizer/configuration, model card, provenance, checksums
+and packaging-time validation. ANE bundles also include the exact original host
+embedding/action tensors they need. No original training checkout is required.
+
+## Port fidelity and limits
+
+The three general-purpose FP16 checkpoints match upstream selected answers on
+**189/189 validation questions**. Each passes 100 repeated calls. ANE FP16 L96
+passes **59/59 fitting questions**, with maximum calibrated-probability drift
+0.002925; W8 passes the same subset with drift 0.014393 under an unchanged 0.02
+gate. Six- and four-bit experiments failed that gate and are not published weights.
+These are conversion-fidelity fixtures, not proof of general task accuracy.
+
+A separately exported FP16 ANE L1024 graph passes the complete **63/63** fixture,
+but an actual 1024-token request takes about **91.7 ms** in its serial screen.
+The short ANE result does not establish a long-context advantage. A 600-step
+paired Snake check matches **600/600 actions**, with zero deaths and zero shield
+interventions; the current ANE adapter's three sequential calls do not establish
+a consistent full-game speedup over compiled MLX.
+
+The ordinary SDPA Core ML export and the ANE graph are different implementations.
+The ordinary export defaults to CPU+GPU after unrestricted RangeDim GPU shapes
+failed local fidelity checks. Changing its device setting alone does not reproduce
+the ANE result. The ANE rewrite uses BC1L activations, 1×1 projections and per-head
+attention; its plan and a separate Instruments trace support Neural Engine work.
+CPU still handles input/output boundaries.
+
+## Documentation and reproducibility
+
+- [Install and Python/CLI API](https://github.com/mizorewww/laya-coreml/blob/main/docs/USAGE.md)
+- [Snake demo and media](https://github.com/mizorewww/laya-coreml/blob/main/docs/SNAKE_DEMO.md)
+- [Release artifacts and pinned Hub revisions](https://github.com/mizorewww/laya-coreml/blob/main/docs/RELEASE.md)
+- [General Core ML benchmarks](https://github.com/mizorewww/laya-coreml/blob/main/BENCHMARKS.md)
+- [ANE engineering experiments](https://github.com/mizorewww/laya-coreml/blob/main/docs/ANE_ENGINEERING.md)
+- [Mathematical investigation of the 10× target](https://github.com/mizorewww/laya-coreml/blob/main/docs/ANE_MATH.md)
+- [Conversion issues and supported shapes](https://github.com/mizorewww/laya-coreml/blob/main/docs/CONVERSION.md)
+
+To export yourself, install `laya-coreml[convert]` and run
+`laya-coreml convert laya-multilingual models/custom`. ANE research conversion,
+compression and benchmark scripts live in the Git checkout. The inference wheel
+contains the portable runtime and optional terminal demo.
+
+Apache-2.0. Independent port of [Laya](https://github.com/NandhaKishorM/laya), by
+Convai Innovations and contributors, building on the [MLX sibling project](https://github.com/mizorewww/laya-mlx).
+Not an official Convai Innovations or Apple release. See
+[NOTICE](https://github.com/mizorewww/laya-coreml/blob/main/NOTICE).

laya_coreml-0.1.0/laya_coreml/__init__.py

@@ -0,0 +1,6 @@
+"""Core ML runtime for Laya. PyTorch is only needed when converting weights."""
+
+from .agent import Agent, load
+
+__all__ = ["Agent", "load"]
+__version__ = "0.1.0"

laya_coreml-0.1.0/laya_coreml/__main__.py

@@ -0,0 +1,3 @@
+from .cli import main
+
+main()