ameva-vulkan-runtime 1.0.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,84 @@
1
+ Metadata-Version: 2.4
2
+ Name: ameva-vulkan-runtime
3
+ Version: 1.0.0
4
+ Summary: Unified Cross-Modal Vulkan GPU Acceleration Runtime & HAL for Mobile Android
5
+ Home-page: https://uno-km.vercel.app/lib/vulkan/
6
+ Author: Eunho Kim
7
+ Author-email: Eunho Kim <contact@uno-km.com>
8
+ License: Apache-2.0
9
+ Project-URL: Homepage, https://uno-km.vercel.app/lib/vulkan/
10
+ Project-URL: Repository, https://github.com/uno-km/ameva-vulkan-runtime
11
+ Project-URL: Documentation, https://uno-km.vercel.app/lib/vulkan/
12
+ Keywords: vulkan,gpu,android,termux,acceleration,adreno,mali,hal,ameva
13
+ Classifier: Development Status :: 5 - Production/Stable
14
+ Classifier: Intended Audience :: Developers
15
+ Classifier: License :: OSI Approved :: Apache Software License
16
+ Classifier: Operating System :: POSIX :: Linux
17
+ Classifier: Operating System :: Android
18
+ Classifier: Programming Language :: Python :: 3
19
+ Classifier: Programming Language :: Python :: 3.8
20
+ Classifier: Programming Language :: Python :: 3.9
21
+ Classifier: Programming Language :: Python :: 3.10
22
+ Classifier: Programming Language :: Python :: 3.11
23
+ Classifier: Programming Language :: Python :: 3.12
24
+ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
25
+ Requires-Python: >=3.8
26
+ Description-Content-Type: text/markdown
27
+ Provides-Extra: stt
28
+ Requires-Dist: termux-stt>=1.1.1; extra == "stt"
29
+ Provides-Extra: diffusion
30
+ Requires-Dist: termux-diffusion>=1.3.1; extra == "diffusion"
31
+ Provides-Extra: bitnet
32
+ Requires-Dist: termux-bitnet>=1.0.0; extra == "bitnet"
33
+ Provides-Extra: llamacpp
34
+ Requires-Dist: termux-llamacpp>=1.0.0; extra == "llamacpp"
35
+ Provides-Extra: tts
36
+ Requires-Dist: termux-tts>=1.0.0; extra == "tts"
37
+ Provides-Extra: vision
38
+ Requires-Dist: termux-vision>=1.0.0; extra == "vision"
39
+ Provides-Extra: all
40
+ Requires-Dist: termux-stt>=1.1.1; extra == "all"
41
+ Requires-Dist: termux-diffusion>=1.3.1; extra == "all"
42
+ Requires-Dist: termux-bitnet>=1.0.0; extra == "all"
43
+ Requires-Dist: termux-llamacpp>=1.0.0; extra == "all"
44
+ Requires-Dist: termux-tts>=1.0.0; extra == "all"
45
+ Requires-Dist: termux-vision>=1.0.0; extra == "all"
46
+ Dynamic: author
47
+ Dynamic: home-page
48
+ Dynamic: requires-python
49
+
50
+ # AMEVA-Vulkan-Runtime (Python)
51
+
52
+ [![PyPI](https://img.shields.io/pypi/v/ameva-vulkan-runtime.svg?style=flat-square&color=0369a1)](https://pypi.org/project/ameva-vulkan-runtime/)
53
+ [![Python](https://img.shields.io/pypi/pyversions/ameva-vulkan-runtime.svg?style=flat-square)](https://pypi.org/project/ameva-vulkan-runtime/)
54
+ [![License](https://img.shields.io/badge/License-Apache_2.0-004499.svg?style=flat-square)](https://github.com/uno-km/ameva-vulkan-runtime)
55
+
56
+ > **안드로이드 모바일 환경을 위한 통합 크로스 모달 Vulkan GPU 가속 런타임 및 하드웨어 추상화 계층(HAL)**
57
+ > *Unified Cross-Modal Vulkan GPU Acceleration Runtime & HAL for Mobile Android*
58
+
59
+ ## Installation
60
+
61
+ ```bash
62
+ pip install ameva-vulkan-runtime
63
+ ```
64
+
65
+ ## Quickstart
66
+
67
+ ```python
68
+ import ameva_vulkan_runtime as avr
69
+ doctor = avr.Doctor()
70
+ report = doctor.run_self_test()
71
+ print(f"GPU Backend Status: {report.status}, Device: {report.device_name}")
72
+ ctx = avr.create_context(device="auto", memory_limit_mb=1024)
73
+ print(f"Context initialized via: {ctx.loader_path} (API {ctx.vulkan_version})")
74
+ ```
75
+
76
+ ## Description
77
+ Provides a single, zero-hardcoded C++20 Vulkan Hardware Abstraction Layer (HAL) and universal runtime for STT, Vision, LLM, Diffusion, and Training with a granular 12-stage validation hierarchy (V0-V11) and zero-data-loss auto-recovery.
78
+
79
+ ## Documentation
80
+ - [Official Documentation & API Reference](https://uno-km.vercel.app/lib/ameva-vulkan-runtime/)
81
+ - [GitHub Repository](https://github.com/uno-km/ameva-vulkan-runtime)
82
+
83
+ ## License
84
+ Apache-2.0 License. Copyright (c) 2026 Eunho Kim (@uno-km).
@@ -0,0 +1,60 @@
1
+ # AMEVA-Vulkan-Runtime
2
+
3
+ [![PyPI](https://img.shields.io/pypi/v/ameva-vulkan-runtime.svg?style=flat-square&color=0369a1)](https://pypi.org/project/ameva-vulkan-runtime/)
4
+ [![Python](https://img.shields.io/pypi/pyversions/ameva-vulkan-runtime.svg?style=flat-square)](https://pypi.org/project/ameva-vulkan-runtime/)
5
+ [![npm](https://img.shields.io/npm/v/ameva-vulkan-runtime.svg?style=flat-square&color=b91c1c)](https://www.npmjs.com/package/ameva-vulkan-runtime)
6
+ [![npm downloads](https://img.shields.io/npm/dm/ameva-vulkan-runtime.svg?style=flat-square&color=b91c1c)](https://www.npmjs.com/package/ameva-vulkan-runtime)
7
+ [![License](https://img.shields.io/badge/License-Apache_2.0-004499.svg?style=flat-square)](https://github.com/uno-km/ameva-vulkan-runtime)
8
+
9
+ > **안드로이드 모바일 환경을 위한 통합 크로스 모달 Vulkan GPU 가속 런타임 및 하드웨어 추상화 계층(HAL)**
10
+ > *Unified Cross-Modal Vulkan GPU Acceleration Runtime & HAL for Mobile Android*
11
+
12
+ ---
13
+
14
+ ## 📌 Architecture & Overview
15
+
16
+ 단일 C++20 Vulkan 하드웨어 추상화 계층(HAL)과 통합 런타임을 통해 STT, 비전, LLM, 디퓨전, 트레이닝 전 모달리티를 가속하며, 12단계 정밀 자체 검증(V0~V11)과 무손실 자동 복구 체계를 제공합니다.
17
+
18
+ Provides a single, zero-hardcoded C++20 Vulkan Hardware Abstraction Layer (HAL) and universal runtime for STT, Vision, LLM, Diffusion, and Training with a granular 12-stage validation hierarchy (V0-V11) and zero-data-loss auto-recovery.
19
+
20
+ ---
21
+
22
+ ## 🚀 Installation & Quickstart
23
+
24
+ ### Python (PyPI)
25
+ ```bash
26
+ pip install ameva-vulkan-runtime
27
+ ```
28
+ ```python
29
+ import ameva_vulkan_runtime as avr
30
+ doctor = avr.Doctor()
31
+ report = doctor.run_self_test()
32
+ print(f"GPU Backend Status: {report.status}, Device: {report.device_name}")
33
+ ctx = avr.create_context(device="auto", memory_limit_mb=1024)
34
+ print(f"Context initialized via: {ctx.loader_path} (API {ctx.vulkan_version})")
35
+ ```
36
+
37
+ ### Node.js / TypeScript (npm)
38
+ ```bash
39
+ npm install ameva-vulkan-runtime
40
+ ```
41
+ ```typescript
42
+ import { Doctor, createContext } from "ameva-vulkan-runtime";
43
+ const doctor = new Doctor();
44
+ const report = await doctor.runSelfTest();
45
+ console.log(`GPU Status: ${report.status}, GPU: ${report.deviceName}`);
46
+ const ctx = await createContext({ device: "auto" });
47
+ console.log(`Vulkan Context Ready on ${ctx.deviceName}`);
48
+ ```
49
+
50
+ ---
51
+
52
+ ## 📖 Official Documentation & Benchmarks
53
+ - [Official Architecture & API Reference](https://uno-km.vercel.app/lib/ameva-vulkan-runtime/)
54
+ - [Ecosystem Metrics & Registry Stats](https://uno-km.vercel.app/foundation/metrics)
55
+ - [AMEVA Open-Source Foundation Portal](https://uno-km.vercel.app/foundation/index.html)
56
+
57
+ ---
58
+
59
+ ## 📄 License
60
+ Licensed under the Apache-2.0 License. Copyright (c) 2026 Eunho Kim ([@uno-km](https://github.com/uno-km)).
@@ -0,0 +1,35 @@
1
+ # AMEVA-Vulkan-Runtime (Python)
2
+
3
+ [![PyPI](https://img.shields.io/pypi/v/ameva-vulkan-runtime.svg?style=flat-square&color=0369a1)](https://pypi.org/project/ameva-vulkan-runtime/)
4
+ [![Python](https://img.shields.io/pypi/pyversions/ameva-vulkan-runtime.svg?style=flat-square)](https://pypi.org/project/ameva-vulkan-runtime/)
5
+ [![License](https://img.shields.io/badge/License-Apache_2.0-004499.svg?style=flat-square)](https://github.com/uno-km/ameva-vulkan-runtime)
6
+
7
+ > **안드로이드 모바일 환경을 위한 통합 크로스 모달 Vulkan GPU 가속 런타임 및 하드웨어 추상화 계층(HAL)**
8
+ > *Unified Cross-Modal Vulkan GPU Acceleration Runtime & HAL for Mobile Android*
9
+
10
+ ## Installation
11
+
12
+ ```bash
13
+ pip install ameva-vulkan-runtime
14
+ ```
15
+
16
+ ## Quickstart
17
+
18
+ ```python
19
+ import ameva_vulkan_runtime as avr
20
+ doctor = avr.Doctor()
21
+ report = doctor.run_self_test()
22
+ print(f"GPU Backend Status: {report.status}, Device: {report.device_name}")
23
+ ctx = avr.create_context(device="auto", memory_limit_mb=1024)
24
+ print(f"Context initialized via: {ctx.loader_path} (API {ctx.vulkan_version})")
25
+ ```
26
+
27
+ ## Description
28
+ Provides a single, zero-hardcoded C++20 Vulkan Hardware Abstraction Layer (HAL) and universal runtime for STT, Vision, LLM, Diffusion, and Training with a granular 12-stage validation hierarchy (V0-V11) and zero-data-loss auto-recovery.
29
+
30
+ ## Documentation
31
+ - [Official Documentation & API Reference](https://uno-km.vercel.app/lib/ameva-vulkan-runtime/)
32
+ - [GitHub Repository](https://github.com/uno-km/ameva-vulkan-runtime)
33
+
34
+ ## License
35
+ Apache-2.0 License. Copyright (c) 2026 Eunho Kim (@uno-km).
@@ -0,0 +1,59 @@
1
+ [build-system]
2
+ requires = ["setuptools>=61.0", "wheel"]
3
+ build-backend = "setuptools.build_meta"
4
+
5
+ [project]
6
+ name = "ameva-vulkan-runtime"
7
+ version = "1.0.0"
8
+ description = "Unified Cross-Modal Vulkan GPU Acceleration Runtime & HAL for Mobile Android"
9
+ readme = "README.pypi.md"
10
+ requires-python = ">=3.8"
11
+ license = { text = "Apache-2.0" }
12
+ authors = [{ name = "Eunho Kim", email = "contact@uno-km.com" }]
13
+ keywords = ["vulkan", "gpu", "android", "termux", "acceleration", "adreno", "mali", "hal", "ameva"]
14
+ classifiers = [
15
+ "Development Status :: 5 - Production/Stable",
16
+ "Intended Audience :: Developers",
17
+ "License :: OSI Approved :: Apache Software License",
18
+ "Operating System :: POSIX :: Linux",
19
+ "Operating System :: Android",
20
+ "Programming Language :: Python :: 3",
21
+ "Programming Language :: Python :: 3.8",
22
+ "Programming Language :: Python :: 3.9",
23
+ "Programming Language :: Python :: 3.10",
24
+ "Programming Language :: Python :: 3.11",
25
+ "Programming Language :: Python :: 3.12",
26
+ "Topic :: Scientific/Engineering :: Artificial Intelligence",
27
+ ]
28
+
29
+ [project.scripts]
30
+ ameva-gpu = "ameva_vulkan_runtime.cli:main"
31
+
32
+ [project.urls]
33
+ Homepage = "https://uno-km.vercel.app/lib/vulkan/"
34
+ Repository = "https://github.com/uno-km/ameva-vulkan-runtime"
35
+ Documentation = "https://uno-km.vercel.app/lib/vulkan/"
36
+
37
+ # --------------------------------------------------------------------------
38
+ # Optional extras — 각 모달리티 패키지와의 통합을 위한 선택적 의존성.
39
+ # ameva-vulkan-runtime 자체는 이 의존성 없이도 독립 실행 가능합니다.
40
+ #
41
+ # 설치 예시:
42
+ # pip install ameva-vulkan-runtime[stt] # STT 모달리티
43
+ # pip install ameva-vulkan-runtime[all] # 전체 6대 모달리티
44
+ # --------------------------------------------------------------------------
45
+ [project.optional-dependencies]
46
+ stt = ["termux-stt>=1.1.1"]
47
+ diffusion = ["termux-diffusion>=1.3.1"]
48
+ bitnet = ["termux-bitnet>=1.0.0"]
49
+ llamacpp = ["termux-llamacpp>=1.0.0"]
50
+ tts = ["termux-tts>=1.0.0"]
51
+ vision = ["termux-vision>=1.0.0"]
52
+ all = [
53
+ "termux-stt>=1.1.1",
54
+ "termux-diffusion>=1.3.1",
55
+ "termux-bitnet>=1.0.0",
56
+ "termux-llamacpp>=1.0.0",
57
+ "termux-tts>=1.0.0",
58
+ "termux-vision>=1.0.0",
59
+ ]
@@ -0,0 +1,59 @@
1
+ """
2
+ AMEVA Unified Vulkan Acceleration Runtime & SDK
3
+ """
4
+ __version__ = "1.0.0"
5
+
6
+ from .core import VulkanContext, create_context
7
+ from .doctor import Doctor, DiagnosticReport, StageReport
8
+ from .protocol import IVulkanConsumer, BindingResult
9
+ from .platform import is_termux, is_android, is_proot, get_termux_prefix, get_termux_home
10
+ from .exceptions import (
11
+ AmevaRuntimeError,
12
+ PlatformNotSupportedError,
13
+ DriverQuirkViolationError,
14
+ BufferAllocationError,
15
+ PipelineCreationError,
16
+ )
17
+ from .adapters import (
18
+ SttAdapter,
19
+ DiffusionAdapter,
20
+ BitnetAdapter,
21
+ LlamaCppAdapter,
22
+ TtsAdapter,
23
+ VisionAdapter,
24
+ )
25
+
26
+ def is_available() -> bool:
27
+ """현재 하드웨어에서 Vulkan 가속이 지원되는지 확인합니다."""
28
+ return Doctor().quick_probe()
29
+
30
+ __all__ = [
31
+ "VulkanContext",
32
+ "create_context",
33
+ "Doctor",
34
+ "DiagnosticReport",
35
+ "StageReport",
36
+ "IVulkanConsumer",
37
+ "BindingResult",
38
+ # Platform utilities (SSOT for uno-km ecosystem)
39
+ "is_termux",
40
+ "is_android",
41
+ "is_proot",
42
+ "get_termux_prefix",
43
+ "get_termux_home",
44
+ # Exceptions
45
+ "AmevaRuntimeError",
46
+ "PlatformNotSupportedError",
47
+ "DriverQuirkViolationError",
48
+ "BufferAllocationError",
49
+ "PipelineCreationError",
50
+ # Adapters
51
+ "SttAdapter",
52
+ "DiffusionAdapter",
53
+ "BitnetAdapter",
54
+ "LlamaCppAdapter",
55
+ "TtsAdapter",
56
+ "VisionAdapter",
57
+ "is_available",
58
+ ]
59
+