vllm-mlx 0.2.0__tar.gz

vllm_mlx-0.2.0/PKG-INFO

@@ -0,0 +1,291 @@
+Metadata-Version: 2.4
+Name: vllm-mlx
+Version: 0.2.0
+Summary: vLLM-like inference for Apple Silicon - GPU-accelerated Text, Image, Video & Audio on Mac
+Author: vllm-mlx contributors
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/vllm-mlx/vllm-mlx
+Project-URL: Documentation, https://github.com/vllm-mlx/vllm-mlx#readme
+Project-URL: Repository, https://github.com/vllm-mlx/vllm-mlx
+Keywords: llm,mlx,apple-silicon,vllm,inference,transformers
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: MacOS
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: mlx>=0.29.0
+Requires-Dist: mlx-lm>=0.20.0
+Requires-Dist: mlx-vlm>=0.1.0
+Requires-Dist: transformers<5.0.0,>=4.40.0
+Requires-Dist: tokenizers>=0.19.0
+Requires-Dist: huggingface-hub>=0.23.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: pillow>=10.0.0
+Requires-Dist: tqdm>=4.66.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: gradio>=4.0.0
+Requires-Dist: requests>=2.28.0
+Requires-Dist: tabulate>=0.9.0
+Requires-Dist: opencv-python>=4.8.0
+Requires-Dist: psutil>=5.9.0
+Requires-Dist: fastapi>=0.100.0
+Requires-Dist: uvicorn>=0.23.0
+Requires-Dist: mcp>=1.0.0
+Requires-Dist: jsonschema>=4.0.0
+Requires-Dist: mlx-audio>=0.2.9
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: mypy>=1.0.0; extra == "dev"
+Provides-Extra: vllm
+Requires-Dist: vllm>=0.4.0; extra == "vllm"
+Provides-Extra: vision
+Requires-Dist: torch>=2.3.0; extra == "vision"
+Requires-Dist: torchvision>=0.18.0; extra == "vision"
+Provides-Extra: audio
+Requires-Dist: mlx-audio>=0.2.9; extra == "audio"
+Requires-Dist: sounddevice>=0.4.0; extra == "audio"
+Requires-Dist: soundfile>=0.12.0; extra == "audio"
+Requires-Dist: scipy>=1.10.0; extra == "audio"
+Requires-Dist: numba>=0.57.0; extra == "audio"
+Requires-Dist: tiktoken>=0.5.0; extra == "audio"
+Requires-Dist: misaki[ja,zh]>=0.5.0; extra == "audio"
+Requires-Dist: spacy>=3.7.0; extra == "audio"
+Requires-Dist: num2words>=0.5.0; extra == "audio"
+Requires-Dist: loguru>=0.7.0; extra == "audio"
+Requires-Dist: phonemizer>=3.2.0; extra == "audio"
+Requires-Dist: ordered_set>=4.1.0; extra == "audio"
+Requires-Dist: cn2an>=0.5.0; extra == "audio"
+Requires-Dist: fugashi>=1.3.0; extra == "audio"
+Requires-Dist: unidic-lite>=1.0.0; extra == "audio"
+Requires-Dist: jieba>=0.42.0; extra == "audio"
+
+# vLLM-MLX
+
+**vLLM-like inference for Apple Silicon** - GPU-accelerated Text, Image, Video & Audio on Mac
+
+[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+[![Apple Silicon](https://img.shields.io/badge/Apple-Silicon-black.svg)](https://support.apple.com/en-us/HT211814)
+[![GitHub](https://img.shields.io/badge/GitHub-waybarrios%2Fvllm--mlx-blue?logo=github)](https://github.com/waybarrios/vllm-mlx)
+
+## Overview
+
+vllm-mlx brings native Apple Silicon GPU acceleration to vLLM by integrating:
+
+- **[MLX](https://github.com/ml-explore/mlx)**: Apple's ML framework with unified memory and Metal kernels
+- **[mlx-lm](https://github.com/ml-explore/mlx-lm)**: Optimized LLM inference with KV cache and quantization
+- **[mlx-vlm](https://github.com/Blaizzy/mlx-vlm)**: Vision-language models for multimodal inference
+- **[mlx-audio](https://github.com/Blaizzy/mlx-audio)**: Speech-to-Text and Text-to-Speech with native voices
+
+## Features
+
+- **Multimodal** - Text, Image, Video & Audio in one platform
+- **Native GPU acceleration** on Apple Silicon (M1, M2, M3, M4)
+- **Native TTS voices** - Spanish, French, Chinese, Japanese + 5 more languages
+- **OpenAI API compatible** - drop-in replacement for OpenAI client
+- **MCP Tool Calling** - integrate external tools via Model Context Protocol
+- **Paged KV Cache** - memory-efficient caching with prefix sharing
+- **Continuous Batching** - high throughput for multiple concurrent users
+
+## Quick Start
+
+### Installation
+
+```bash
+git clone https://github.com/waybarrios/vllm-mlx.git
+cd vllm-mlx
+pip install -e .
+```
+
+### Start Server
+
+```bash
+# Simple mode (single user, max throughput)
+vllm-mlx serve mlx-community/Llama-3.2-3B-Instruct-4bit --port 8000
+
+# Continuous batching (multiple users)
+vllm-mlx serve mlx-community/Llama-3.2-3B-Instruct-4bit --port 8000 --continuous-batching
+```
+
+### Use with OpenAI SDK
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://localhost:8000/v1", api_key="not-needed")
+
+response = client.chat.completions.create(
+    model="default",
+    messages=[{"role": "user", "content": "Hello!"}],
+)
+print(response.choices[0].message.content)
+```
+
+### Multimodal (Images & Video)
+
+```bash
+vllm-mlx serve mlx-community/Qwen3-VL-4B-Instruct-3bit --port 8000
+```
+
+```python
+response = client.chat.completions.create(
+    model="default",
+    messages=[{
+        "role": "user",
+        "content": [
+            {"type": "text", "text": "What's in this image?"},
+            {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
+        ]
+    }]
+)
+```
+
+### Audio (TTS/STT)
+
+```bash
+# Install audio dependencies
+pip install vllm-mlx[audio]
+python -m spacy download en_core_web_sm
+brew install espeak-ng  # macOS, for non-English languages
+```
+
+```bash
+# Text-to-Speech (English)
+python examples/tts_example.py "Hello, how are you?" --play
+
+# Text-to-Speech (Spanish)
+python examples/tts_multilingual.py "Hola mundo" --lang es --play
+
+# List available models and languages
+python examples/tts_multilingual.py --list-models
+python examples/tts_multilingual.py --list-languages
+```
+
+**Supported TTS Models:**
+| Model | Languages | Description |
+|-------|-----------|-------------|
+| Kokoro | EN, ES, FR, JA, ZH, IT, PT, HI | Fast, 82M params, 11 voices |
+| Chatterbox | 15+ languages | Expressive, voice cloning |
+| VibeVoice | EN | Realtime, low latency |
+| VoxCPM | ZH, EN | High quality Chinese/English |
+
+## Documentation
+
+For full documentation, see the [docs](docs/) directory:
+
+- **Getting Started**
+  - [Installation](docs/getting-started/installation.md)
+  - [Quick Start](docs/getting-started/quickstart.md)
+
+- **User Guides**
+  - [OpenAI-Compatible Server](docs/guides/server.md)
+  - [Python API](docs/guides/python-api.md)
+  - [Multimodal (Images & Video)](docs/guides/multimodal.md)
+  - [Audio (STT/TTS)](docs/guides/audio.md)
+  - [MCP & Tool Calling](docs/guides/mcp-tools.md)
+  - [Continuous Batching](docs/guides/continuous-batching.md)
+
+- **Reference**
+  - [CLI Commands](docs/reference/cli.md)
+  - [Supported Models](docs/reference/models.md)
+  - [Configuration](docs/reference/configuration.md)
+
+- **Benchmarks**
+  - [LLM Benchmarks](docs/benchmarks/llm.md)
+  - [Image Benchmarks](docs/benchmarks/image.md)
+  - [Video Benchmarks](docs/benchmarks/video.md)
+
+## Architecture
+
+```
+┌─────────────────────────────────────────────┐
+│              vLLM API Layer                 │
+│     (OpenAI-compatible interface)           │
+└─────────────────────────────────────────────┘
+                      │
+                      ▼
+┌─────────────────────────────────────────────┐
+│              MLXPlatform                    │
+│   (vLLM platform plugin for Apple Silicon) │
+└─────────────────────────────────────────────┘
+                      │
+          ┌───────────┴───────────┐
+          ▼                       ▼
+┌──────────────────┐   ┌──────────────────┐
+│     mlx-lm       │   │     mlx-vlm       │
+│  (LLM inference) │   │  (MLLM inference) │
+└──────────────────┘   └──────────────────┘
+          │                       │
+          └───────────┬───────────┘
+                      ▼
+┌─────────────────────────────────────────────┐
+│                   MLX                       │
+│    (Apple ML Framework - Metal kernels)    │
+└─────────────────────────────────────────────┘
+```
+
+## Performance
+
+**LLM Performance (M4 Max, 128GB):**
+
+| Model | Speed | Memory |
+|-------|-------|--------|
+| Qwen3-0.6B-8bit | 402 tok/s | 0.7 GB |
+| Llama-3.2-1B-4bit | 464 tok/s | 0.7 GB |
+| Llama-3.2-3B-4bit | 200 tok/s | 1.8 GB |
+
+**Continuous Batching (5 concurrent requests):**
+
+| Model | Single | Batched | Speedup |
+|-------|--------|---------|---------|
+| Qwen3-0.6B-8bit | 328 tok/s | 1112 tok/s | **3.4x** |
+| Llama-3.2-1B-4bit | 299 tok/s | 613 tok/s | **2.0x** |
+
+See [benchmarks](docs/benchmarks/) for detailed results.
+
+## Contributing
+
+We welcome contributions! See [Contributing Guide](docs/development/contributing.md) for details.
+
+- Bug fixes and improvements
+- Performance optimizations
+- Documentation improvements
+- Benchmarks on different Apple Silicon chips
+
+Submit PRs to: [https://github.com/waybarrios/vllm-mlx](https://github.com/waybarrios/vllm-mlx)
+
+## License
+
+Apache 2.0 - see [LICENSE](LICENSE) for details.
+
+## Citation
+
+If you use vLLM-MLX in your research or project, please cite:
+
+```bibtex
+@software{vllm_mlx2025,
+  author = {Barrios, Wayner},
+  title = {vLLM-MLX: Apple Silicon MLX Backend for vLLM},
+  year = {2025},
+  url = {https://github.com/waybarrios/vllm-mlx},
+  note = {Native GPU-accelerated LLM and vision-language model inference on Apple Silicon}
+}
+```
+
+## Acknowledgments
+
+- [MLX](https://github.com/ml-explore/mlx) - Apple's ML framework
+- [mlx-lm](https://github.com/ml-explore/mlx-lm) - LLM inference library
+- [mlx-vlm](https://github.com/Blaizzy/mlx-vlm) - Vision-language models
+- [vLLM](https://github.com/vllm-project/vllm) - High-throughput LLM serving

vllm_mlx-0.2.0/README.md

@@ -0,0 +1,219 @@
+# vLLM-MLX
+
+**vLLM-like inference for Apple Silicon** - GPU-accelerated Text, Image, Video & Audio on Mac
+
+[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+[![Apple Silicon](https://img.shields.io/badge/Apple-Silicon-black.svg)](https://support.apple.com/en-us/HT211814)
+[![GitHub](https://img.shields.io/badge/GitHub-waybarrios%2Fvllm--mlx-blue?logo=github)](https://github.com/waybarrios/vllm-mlx)
+
+## Overview
+
+vllm-mlx brings native Apple Silicon GPU acceleration to vLLM by integrating:
+
+- **[MLX](https://github.com/ml-explore/mlx)**: Apple's ML framework with unified memory and Metal kernels
+- **[mlx-lm](https://github.com/ml-explore/mlx-lm)**: Optimized LLM inference with KV cache and quantization
+- **[mlx-vlm](https://github.com/Blaizzy/mlx-vlm)**: Vision-language models for multimodal inference
+- **[mlx-audio](https://github.com/Blaizzy/mlx-audio)**: Speech-to-Text and Text-to-Speech with native voices
+
+## Features
+
+- **Multimodal** - Text, Image, Video & Audio in one platform
+- **Native GPU acceleration** on Apple Silicon (M1, M2, M3, M4)
+- **Native TTS voices** - Spanish, French, Chinese, Japanese + 5 more languages
+- **OpenAI API compatible** - drop-in replacement for OpenAI client
+- **MCP Tool Calling** - integrate external tools via Model Context Protocol
+- **Paged KV Cache** - memory-efficient caching with prefix sharing
+- **Continuous Batching** - high throughput for multiple concurrent users
+
+## Quick Start
+
+### Installation
+
+```bash
+git clone https://github.com/waybarrios/vllm-mlx.git
+cd vllm-mlx
+pip install -e .
+```
+
+### Start Server
+
+```bash
+# Simple mode (single user, max throughput)
+vllm-mlx serve mlx-community/Llama-3.2-3B-Instruct-4bit --port 8000
+
+# Continuous batching (multiple users)
+vllm-mlx serve mlx-community/Llama-3.2-3B-Instruct-4bit --port 8000 --continuous-batching
+```
+
+### Use with OpenAI SDK
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://localhost:8000/v1", api_key="not-needed")
+
+response = client.chat.completions.create(
+    model="default",
+    messages=[{"role": "user", "content": "Hello!"}],
+)
+print(response.choices[0].message.content)
+```
+
+### Multimodal (Images & Video)
+
+```bash
+vllm-mlx serve mlx-community/Qwen3-VL-4B-Instruct-3bit --port 8000
+```
+
+```python
+response = client.chat.completions.create(
+    model="default",
+    messages=[{
+        "role": "user",
+        "content": [
+            {"type": "text", "text": "What's in this image?"},
+            {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
+        ]
+    }]
+)
+```
+
+### Audio (TTS/STT)
+
+```bash
+# Install audio dependencies
+pip install vllm-mlx[audio]
+python -m spacy download en_core_web_sm
+brew install espeak-ng  # macOS, for non-English languages
+```
+
+```bash
+# Text-to-Speech (English)
+python examples/tts_example.py "Hello, how are you?" --play
+
+# Text-to-Speech (Spanish)
+python examples/tts_multilingual.py "Hola mundo" --lang es --play
+
+# List available models and languages
+python examples/tts_multilingual.py --list-models
+python examples/tts_multilingual.py --list-languages
+```
+
+**Supported TTS Models:**
+| Model | Languages | Description |
+|-------|-----------|-------------|
+| Kokoro | EN, ES, FR, JA, ZH, IT, PT, HI | Fast, 82M params, 11 voices |
+| Chatterbox | 15+ languages | Expressive, voice cloning |
+| VibeVoice | EN | Realtime, low latency |
+| VoxCPM | ZH, EN | High quality Chinese/English |
+
+## Documentation
+
+For full documentation, see the [docs](docs/) directory:
+
+- **Getting Started**
+  - [Installation](docs/getting-started/installation.md)
+  - [Quick Start](docs/getting-started/quickstart.md)
+
+- **User Guides**
+  - [OpenAI-Compatible Server](docs/guides/server.md)
+  - [Python API](docs/guides/python-api.md)
+  - [Multimodal (Images & Video)](docs/guides/multimodal.md)
+  - [Audio (STT/TTS)](docs/guides/audio.md)
+  - [MCP & Tool Calling](docs/guides/mcp-tools.md)
+  - [Continuous Batching](docs/guides/continuous-batching.md)
+
+- **Reference**
+  - [CLI Commands](docs/reference/cli.md)
+  - [Supported Models](docs/reference/models.md)
+  - [Configuration](docs/reference/configuration.md)
+
+- **Benchmarks**
+  - [LLM Benchmarks](docs/benchmarks/llm.md)
+  - [Image Benchmarks](docs/benchmarks/image.md)
+  - [Video Benchmarks](docs/benchmarks/video.md)
+
+## Architecture
+
+```
+┌─────────────────────────────────────────────┐
+│              vLLM API Layer                 │
+│     (OpenAI-compatible interface)           │
+└─────────────────────────────────────────────┘
+                      │
+                      ▼
+┌─────────────────────────────────────────────┐
+│              MLXPlatform                    │
+│   (vLLM platform plugin for Apple Silicon) │
+└─────────────────────────────────────────────┘
+                      │
+          ┌───────────┴───────────┐
+          ▼                       ▼
+┌──────────────────┐   ┌──────────────────┐
+│     mlx-lm       │   │     mlx-vlm       │
+│  (LLM inference) │   │  (MLLM inference) │
+└──────────────────┘   └──────────────────┘
+          │                       │
+          └───────────┬───────────┘
+                      ▼
+┌─────────────────────────────────────────────┐
+│                   MLX                       │
+│    (Apple ML Framework - Metal kernels)    │
+└─────────────────────────────────────────────┘
+```
+
+## Performance
+
+**LLM Performance (M4 Max, 128GB):**
+
+| Model | Speed | Memory |
+|-------|-------|--------|
+| Qwen3-0.6B-8bit | 402 tok/s | 0.7 GB |
+| Llama-3.2-1B-4bit | 464 tok/s | 0.7 GB |
+| Llama-3.2-3B-4bit | 200 tok/s | 1.8 GB |
+
+**Continuous Batching (5 concurrent requests):**
+
+| Model | Single | Batched | Speedup |
+|-------|--------|---------|---------|
+| Qwen3-0.6B-8bit | 328 tok/s | 1112 tok/s | **3.4x** |
+| Llama-3.2-1B-4bit | 299 tok/s | 613 tok/s | **2.0x** |
+
+See [benchmarks](docs/benchmarks/) for detailed results.
+
+## Contributing
+
+We welcome contributions! See [Contributing Guide](docs/development/contributing.md) for details.
+
+- Bug fixes and improvements
+- Performance optimizations
+- Documentation improvements
+- Benchmarks on different Apple Silicon chips
+
+Submit PRs to: [https://github.com/waybarrios/vllm-mlx](https://github.com/waybarrios/vllm-mlx)
+
+## License
+
+Apache 2.0 - see [LICENSE](LICENSE) for details.
+
+## Citation
+
+If you use vLLM-MLX in your research or project, please cite:
+
+```bibtex
+@software{vllm_mlx2025,
+  author = {Barrios, Wayner},
+  title = {vLLM-MLX: Apple Silicon MLX Backend for vLLM},
+  year = {2025},
+  url = {https://github.com/waybarrios/vllm-mlx},
+  note = {Native GPU-accelerated LLM and vision-language model inference on Apple Silicon}
+}
+```
+
+## Acknowledgments
+
+- [MLX](https://github.com/ml-explore/mlx) - Apple's ML framework
+- [mlx-lm](https://github.com/ml-explore/mlx-lm) - LLM inference library
+- [mlx-vlm](https://github.com/Blaizzy/mlx-vlm) - Vision-language models
+- [vLLM](https://github.com/vllm-project/vllm) - High-throughput LLM serving

vllm_mlx-0.2.0/pyproject.toml

@@ -0,0 +1,131 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "vllm-mlx"
+version = "0.2.0"
+description = "vLLM-like inference for Apple Silicon - GPU-accelerated Text, Image, Video & Audio on Mac"
+readme = "README.md"
+license = {text = "Apache-2.0"}
+requires-python = ">=3.10"
+authors = [
+    {name = "vllm-mlx contributors"}
+]
+keywords = ["llm", "mlx", "apple-silicon", "vllm", "inference", "transformers"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Operating System :: MacOS",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+
+dependencies = [
+    "mlx>=0.29.0",
+    "mlx-lm>=0.20.0",
+    "mlx-vlm>=0.1.0",  # VLM support
+    "transformers>=4.40.0,<5.0.0",
+    "tokenizers>=0.19.0",
+    "huggingface-hub>=0.23.0",
+    "numpy>=1.24.0",
+    "pillow>=10.0.0",
+    "tqdm>=4.66.0",
+    "pyyaml>=6.0",
+    "gradio>=4.0.0",
+    "requests>=2.28.0",
+    "tabulate>=0.9.0",
+    # Video processing for VLM
+    "opencv-python>=4.8.0",
+    # Resource monitoring
+    "psutil>=5.9.0",
+    # Server
+    "fastapi>=0.100.0",
+    "uvicorn>=0.23.0",
+    # MCP (Model Context Protocol) support
+    "mcp>=1.0.0",
+    # JSON Schema validation for structured output
+    "jsonschema>=4.0.0",
+    # Audio support (STT, TTS, audio processing)
+    "mlx-audio>=0.2.9",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0.0",
+    "pytest-asyncio>=0.21.0",
+    "black>=23.0.0",
+    "ruff>=0.1.0",
+    "mypy>=1.0.0",
+]
+vllm = [
+    "vllm>=0.4.0",
+]
+vision = [
+    "torch>=2.3.0",
+    "torchvision>=0.18.0",
+]
+# Audio dependencies for TTS/STT (mlx-audio)
+audio = [
+    "mlx-audio>=0.2.9",
+    "sounddevice>=0.4.0",
+    "soundfile>=0.12.0",
+    "scipy>=1.10.0",
+    "numba>=0.57.0",
+    "tiktoken>=0.5.0",
+    "misaki[zh,ja]>=0.5.0",  # Chinese (zh) and Japanese (ja) support
+    "spacy>=3.7.0",
+    "num2words>=0.5.0",
+    "loguru>=0.7.0",
+    "phonemizer>=3.2.0",
+    # Additional multilingual dependencies
+    "ordered_set>=4.1.0",    # Required for Chinese TTS
+    "cn2an>=0.5.0",          # Chinese number conversion
+    "fugashi>=1.3.0",        # Japanese tokenizer
+    "unidic-lite>=1.0.0",    # Japanese dictionary for fugashi
+    "jieba>=0.42.0",         # Chinese word segmentation
+]
+
+[project.urls]
+Homepage = "https://github.com/vllm-mlx/vllm-mlx"
+Documentation = "https://github.com/vllm-mlx/vllm-mlx#readme"
+Repository = "https://github.com/vllm-mlx/vllm-mlx"
+
+[project.entry-points."vllm.platform_plugins"]
+mlx = "vllm_mlx.plugin:mlx_platform_plugin"
+
+[project.scripts]
+vllm-mlx = "vllm_mlx.cli:main"
+vllm-mlx-serve = "vllm_mlx.server_v2:main"
+vllm-mlx-chat = "vllm_mlx.gradio_app:main"
+vllm-mlx-bench = "vllm_mlx.benchmark:main"
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["vllm_mlx*"]
+
+[tool.black]
+line-length = 88
+target-version = ["py310", "py311", "py312", "py313"]
+
+[tool.ruff]
+line-length = 88
+select = ["E", "F", "W", "I", "N", "UP", "B", "SIM"]
+ignore = ["E501", "B905"]
+
+[tool.mypy]
+python_version = "3.10"
+warn_return_any = true
+warn_unused_configs = true
+ignore_missing_imports = true
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py"]
+asyncio_mode = "auto"

vllm_mlx-0.2.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+