cortex-llm 1.0.3__tar.gz → 1.0.6__tar.gz

cortex_llm-1.0.6/PKG-INFO

@@ -0,0 +1,155 @@
+Metadata-Version: 2.4
+Name: cortex-llm
+Version: 1.0.6
+Summary: GPU-Accelerated LLM Terminal for Apple Silicon
+Home-page: https://github.com/faisalmumtaz/Cortex
+Author: Cortex Development Team
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/faisalmumtaz/Cortex
+Project-URL: Bug Tracker, https://github.com/faisalmumtaz/Cortex/issues
+Project-URL: Documentation, https://github.com/faisalmumtaz/Cortex/wiki
+Keywords: llm,gpu,metal,mps,apple-silicon,ai,machine-learning,terminal,mlx,pytorch
+Platform: darwin
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: MacOS
+Classifier: Environment :: Console
+Classifier: Environment :: GPU
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.1.0
+Requires-Dist: mlx>=0.30.4
+Requires-Dist: mlx-lm>=0.30.5
+Requires-Dist: transformers>=4.36.0
+Requires-Dist: safetensors>=0.4.0
+Requires-Dist: huggingface-hub>=0.19.0
+Requires-Dist: accelerate>=0.25.0
+Requires-Dist: llama-cpp-python>=0.2.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: pydantic>=2.5.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: psutil>=5.9.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: packaging>=23.0
+Requires-Dist: requests>=2.31.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.4.0; 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>=1.8.0; extra == "dev"
+Provides-Extra: optional
+Requires-Dist: sentencepiece>=0.1.99; extra == "optional"
+Requires-Dist: auto-gptq>=0.7.0; extra == "optional"
+Requires-Dist: autoawq>=0.2.0; extra == "optional"
+Requires-Dist: bitsandbytes>=0.41.0; extra == "optional"
+Requires-Dist: optimum>=1.16.0; extra == "optional"
+Requires-Dist: torchvision>=0.16.0; extra == "optional"
+Requires-Dist: torchaudio>=2.1.0; extra == "optional"
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: platform
+Dynamic: requires-python
+
+# Cortex
+
+GPU-accelerated local LLMs on Apple Silicon, built for the terminal.
+
+Cortex is a fast, native CLI for running and fine-tuning LLMs on Apple Silicon using MLX and Metal. It automatically detects chat templates, supports multiple model formats, and keeps your workflow inside the terminal.
+
+## Highlights
+
+- Apple Silicon GPU acceleration via MLX (primary) and PyTorch MPS
+- Multi-format model support: MLX, GGUF, SafeTensors, PyTorch, GPTQ, AWQ
+- Built-in LoRA fine-tuning wizard
+- Chat template auto-detection (ChatML, Llama, Alpaca, Gemma, Reasoning)
+- Conversation history with branching
+
+## Quick Start
+
+```bash
+pipx install cortex-llm
+cortex
+```
+
+Inside Cortex:
+
+- `/download` to fetch a model from HuggingFace
+- `/model` to load or manage models
+- `/status` to confirm GPU acceleration and current settings
+
+## Installation
+
+### Option A: pipx (recommended)
+
+```bash
+pipx install cortex-llm
+```
+
+### Option B: from source
+
+```bash
+git clone https://github.com/faisalmumtaz/Cortex.git
+cd Cortex
+./install.sh
+```
+
+The installer checks Apple Silicon compatibility, creates a venv, installs dependencies from `pyproject.toml`, and sets up the `cortex` command.
+
+## Requirements
+
+- Apple Silicon Mac (M1/M2/M3/M4)
+- macOS 13.3+
+- Python 3.11+
+- 16GB+ unified memory (24GB+ recommended for larger models)
+- Xcode Command Line Tools
+
+## Model Support
+
+Cortex supports:
+
+- **MLX** (recommended)
+- **GGUF** (llama.cpp + Metal)
+- **SafeTensors**
+- **PyTorch** (Transformers + MPS)
+- **GPTQ** / **AWQ** quantized models
+
+## Configuration
+
+Cortex reads `config.yaml` from the current working directory. For tuning GPU memory limits, quantization defaults, and inference parameters, see:
+
+- `docs/configuration.md`
+
+## Documentation
+
+Start here:
+
+- `docs/installation.md`
+- `docs/cli.md`
+- `docs/model-management.md`
+- `docs/troubleshooting.md`
+
+Advanced topics:
+
+- `docs/mlx-acceleration.md`
+- `docs/inference-engine.md`
+- `docs/template-registry.md`
+- `docs/fine-tuning.md`
+- `docs/development.md`
+
+## Contributing
+
+Contributions are welcome. See `docs/development.md` for setup and workflow.
+
+## License
+
+MIT License. See `LICENSE`.
+
+---
+
+Note: Cortex requires Apple Silicon. Intel Macs are not supported.

cortex_llm-1.0.6/README.md

@@ -0,0 +1,97 @@
+# Cortex
+
+GPU-accelerated local LLMs on Apple Silicon, built for the terminal.
+
+Cortex is a fast, native CLI for running and fine-tuning LLMs on Apple Silicon using MLX and Metal. It automatically detects chat templates, supports multiple model formats, and keeps your workflow inside the terminal.
+
+## Highlights
+
+- Apple Silicon GPU acceleration via MLX (primary) and PyTorch MPS
+- Multi-format model support: MLX, GGUF, SafeTensors, PyTorch, GPTQ, AWQ
+- Built-in LoRA fine-tuning wizard
+- Chat template auto-detection (ChatML, Llama, Alpaca, Gemma, Reasoning)
+- Conversation history with branching
+
+## Quick Start
+
+```bash
+pipx install cortex-llm
+cortex
+```
+
+Inside Cortex:
+
+- `/download` to fetch a model from HuggingFace
+- `/model` to load or manage models
+- `/status` to confirm GPU acceleration and current settings
+
+## Installation
+
+### Option A: pipx (recommended)
+
+```bash
+pipx install cortex-llm
+```
+
+### Option B: from source
+
+```bash
+git clone https://github.com/faisalmumtaz/Cortex.git
+cd Cortex
+./install.sh
+```
+
+The installer checks Apple Silicon compatibility, creates a venv, installs dependencies from `pyproject.toml`, and sets up the `cortex` command.
+
+## Requirements
+
+- Apple Silicon Mac (M1/M2/M3/M4)
+- macOS 13.3+
+- Python 3.11+
+- 16GB+ unified memory (24GB+ recommended for larger models)
+- Xcode Command Line Tools
+
+## Model Support
+
+Cortex supports:
+
+- **MLX** (recommended)
+- **GGUF** (llama.cpp + Metal)
+- **SafeTensors**
+- **PyTorch** (Transformers + MPS)
+- **GPTQ** / **AWQ** quantized models
+
+## Configuration
+
+Cortex reads `config.yaml` from the current working directory. For tuning GPU memory limits, quantization defaults, and inference parameters, see:
+
+- `docs/configuration.md`
+
+## Documentation
+
+Start here:
+
+- `docs/installation.md`
+- `docs/cli.md`
+- `docs/model-management.md`
+- `docs/troubleshooting.md`
+
+Advanced topics:
+
+- `docs/mlx-acceleration.md`
+- `docs/inference-engine.md`
+- `docs/template-registry.md`
+- `docs/fine-tuning.md`
+- `docs/development.md`
+
+## Contributing
+
+Contributions are welcome. See `docs/development.md` for setup and workflow.
+
+## License
+
+MIT License. See `LICENSE`.
+
+---
+
+Note: Cortex requires Apple Silicon. Intel Macs are not supported.

{cortex_llm-1.0.3 → cortex_llm-1.0.6}/cortex/__init__.py

@@ -5,7 +5,7 @@ A high-performance terminal interface for running Hugging Face LLMs locally
 with exclusive GPU acceleration via Metal Performance Shaders (MPS) and MLX.
 """
 
-__version__ = "1.0.3"
+__version__ = "1.0.6"
 __author__ = "Cortex Development Team"
 __license__ = "MIT"
 

{cortex_llm-1.0.3 → cortex_llm-1.0.6}/cortex/__main__.py

@@ -9,11 +9,12 @@ import warnings
 # This prevents the semaphore leak warning from transformers library
 os.environ['PYTHONWARNINGS'] = 'ignore::UserWarning:multiprocessing.resource_tracker'
 
-# Silence known MLX deprecation warning surfaced during generation.
-warnings.filterwarnings(
-    "ignore",
-    message=r"mx\.metal\.device_info is deprecated.*",
-)
+# Apply MLX compatibility shims before any MLX/MLX-LM imports.
+try:
+    from cortex.metal.mlx_compat import patch_mlx_lm_device_info
+    patch_mlx_lm_device_info()
+except Exception:
+    pass
 
 # Alternative: Monkey-patch the resource tracker before it's used
 try:

{cortex_llm-1.0.3 → cortex_llm-1.0.6}/cortex/metal/mlx_compat.py

@@ -12,6 +12,19 @@ def _get_device_info(mx) -> dict:
     except Exception:
         return {}
 
+def patch_mlx_device_info() -> None:
+    """Redirect deprecated mx.metal.device_info to mx.device_info when possible."""
+    try:
+        import mlx.core as mx
+    except Exception:
+        return
+
+    if hasattr(mx, "device_info") and hasattr(mx, "metal") and hasattr(mx.metal, "device_info"):
+        try:
+            mx.metal.device_info = mx.device_info  # type: ignore[attr-defined]
+        except Exception:
+            pass
+
 
 def patch_mlx_lm_device_info() -> None:
     """Patch mlx_lm call sites to use mx.device_info() instead of mx.metal.device_info()."""
@@ -24,6 +37,8 @@ def patch_mlx_lm_device_info() -> None:
     if not hasattr(mx, "device_info"):
         return
 
+    patch_mlx_device_info()
+
     try:
         import mlx_lm.generate as mlx_generate
     except Exception:

cortex_llm-1.0.6/cortex_llm.egg-info/PKG-INFO

@@ -0,0 +1,155 @@
+Metadata-Version: 2.4
+Name: cortex-llm
+Version: 1.0.6
+Summary: GPU-Accelerated LLM Terminal for Apple Silicon
+Home-page: https://github.com/faisalmumtaz/Cortex
+Author: Cortex Development Team
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/faisalmumtaz/Cortex
+Project-URL: Bug Tracker, https://github.com/faisalmumtaz/Cortex/issues
+Project-URL: Documentation, https://github.com/faisalmumtaz/Cortex/wiki
+Keywords: llm,gpu,metal,mps,apple-silicon,ai,machine-learning,terminal,mlx,pytorch
+Platform: darwin
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: MacOS
+Classifier: Environment :: Console
+Classifier: Environment :: GPU
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.1.0
+Requires-Dist: mlx>=0.30.4
+Requires-Dist: mlx-lm>=0.30.5
+Requires-Dist: transformers>=4.36.0
+Requires-Dist: safetensors>=0.4.0
+Requires-Dist: huggingface-hub>=0.19.0
+Requires-Dist: accelerate>=0.25.0
+Requires-Dist: llama-cpp-python>=0.2.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: pydantic>=2.5.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: psutil>=5.9.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: packaging>=23.0
+Requires-Dist: requests>=2.31.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.4.0; 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>=1.8.0; extra == "dev"
+Provides-Extra: optional
+Requires-Dist: sentencepiece>=0.1.99; extra == "optional"
+Requires-Dist: auto-gptq>=0.7.0; extra == "optional"
+Requires-Dist: autoawq>=0.2.0; extra == "optional"
+Requires-Dist: bitsandbytes>=0.41.0; extra == "optional"
+Requires-Dist: optimum>=1.16.0; extra == "optional"
+Requires-Dist: torchvision>=0.16.0; extra == "optional"
+Requires-Dist: torchaudio>=2.1.0; extra == "optional"
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: platform
+Dynamic: requires-python
+
+# Cortex
+
+GPU-accelerated local LLMs on Apple Silicon, built for the terminal.
+
+Cortex is a fast, native CLI for running and fine-tuning LLMs on Apple Silicon using MLX and Metal. It automatically detects chat templates, supports multiple model formats, and keeps your workflow inside the terminal.
+
+## Highlights
+
+- Apple Silicon GPU acceleration via MLX (primary) and PyTorch MPS
+- Multi-format model support: MLX, GGUF, SafeTensors, PyTorch, GPTQ, AWQ
+- Built-in LoRA fine-tuning wizard
+- Chat template auto-detection (ChatML, Llama, Alpaca, Gemma, Reasoning)
+- Conversation history with branching
+
+## Quick Start
+
+```bash
+pipx install cortex-llm
+cortex
+```
+
+Inside Cortex:
+
+- `/download` to fetch a model from HuggingFace
+- `/model` to load or manage models
+- `/status` to confirm GPU acceleration and current settings
+
+## Installation
+
+### Option A: pipx (recommended)
+
+```bash
+pipx install cortex-llm
+```
+
+### Option B: from source
+
+```bash
+git clone https://github.com/faisalmumtaz/Cortex.git
+cd Cortex
+./install.sh
+```
+
+The installer checks Apple Silicon compatibility, creates a venv, installs dependencies from `pyproject.toml`, and sets up the `cortex` command.
+
+## Requirements
+
+- Apple Silicon Mac (M1/M2/M3/M4)
+- macOS 13.3+
+- Python 3.11+
+- 16GB+ unified memory (24GB+ recommended for larger models)
+- Xcode Command Line Tools
+
+## Model Support
+
+Cortex supports:
+
+- **MLX** (recommended)
+- **GGUF** (llama.cpp + Metal)
+- **SafeTensors**
+- **PyTorch** (Transformers + MPS)
+- **GPTQ** / **AWQ** quantized models
+
+## Configuration
+
+Cortex reads `config.yaml` from the current working directory. For tuning GPU memory limits, quantization defaults, and inference parameters, see:
+
+- `docs/configuration.md`
+
+## Documentation
+
+Start here:
+
+- `docs/installation.md`
+- `docs/cli.md`
+- `docs/model-management.md`
+- `docs/troubleshooting.md`
+
+Advanced topics:
+
+- `docs/mlx-acceleration.md`
+- `docs/inference-engine.md`
+- `docs/template-registry.md`
+- `docs/fine-tuning.md`
+- `docs/development.md`
+
+## Contributing
+
+Contributions are welcome. See `docs/development.md` for setup and workflow.
+
+## License
+
+MIT License. See `LICENSE`.
+
+---
+
+Note: Cortex requires Apple Silicon. Intel Macs are not supported.

{cortex_llm-1.0.3 → cortex_llm-1.0.6}/cortex_llm.egg-info/requires.txt

@@ -1,6 +1,6 @@
 torch>=2.1.0
-mlx>=0.10.0
-mlx-lm>=0.10.0
+mlx>=0.30.4
+mlx-lm>=0.30.5
 transformers>=4.36.0
 safetensors>=0.4.0
 huggingface-hub>=0.19.0

{cortex_llm-1.0.3 → cortex_llm-1.0.6}/pyproject.toml

@@ -4,10 +4,11 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "cortex-llm"
-version = "1.0.3"
+version = "1.0.6"
 description = "GPU-Accelerated LLM Terminal for Apple Silicon"
 readme = "README.md"
-license = {text = "MIT"}
+license = "MIT"
+license-files = ["LICENSE"]
 authors = [
     {name = "Cortex Development Team"},
 ]
@@ -16,7 +17,6 @@ classifiers = [
     "Development Status :: 4 - Beta",
     "Intended Audience :: Developers",
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
-    "License :: OSI Approved :: MIT License",
     "Programming Language :: Python :: 3",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
@@ -30,8 +30,8 @@ keywords = ["llm", "gpu", "metal", "mps", "apple-silicon", "ai", "machine-learni
 dependencies = [
     # Core ML/AI Libraries
     "torch>=2.1.0",
-    "mlx>=0.10.0",
-    "mlx-lm>=0.10.0",
+    "mlx>=0.30.4",
+    "mlx-lm>=0.30.5",
     "transformers>=4.36.0",
     "safetensors>=0.4.0",
     "huggingface-hub>=0.19.0",
@@ -85,7 +85,6 @@ Documentation = "https://github.com/faisalmumtaz/Cortex/wiki"
 [tool.setuptools]
 packages = ["cortex", "cortex.metal", "cortex.ui", "cortex.fine_tuning", "cortex.quantization", "cortex.template_registry", "cortex.template_registry.template_profiles", "cortex.template_registry.template_profiles.complex", "cortex.template_registry.template_profiles.standard"]
 include-package-data = true
-license-files = ["LICENSE"]
 
 [tool.setuptools.package-data]
 cortex = ["config.yaml"]

{cortex_llm-1.0.3 → cortex_llm-1.0.6}/setup.py

@@ -36,7 +36,6 @@ setup(
         "Development Status :: 4 - Beta",
         "Intended Audience :: Developers",
         "Topic :: Scientific/Engineering :: Artificial Intelligence",
-        "License :: OSI Approved :: MIT License",
         "Programming Language :: Python :: 3",
         "Programming Language :: Python :: 3.11",
         "Programming Language :: Python :: 3.12",
@@ -60,8 +59,9 @@ setup(
             "auto-gptq>=0.7.0",
             "autoawq>=0.2.0",
             "bitsandbytes>=0.41.0",
-            "llama-cpp-python>=0.2.0",
             "optimum>=1.16.0",
+            "torchvision>=0.16.0",
+            "torchaudio>=2.1.0",
         ],
     },
     entry_points={
@@ -79,4 +79,4 @@ setup(
         "llm", "gpu", "metal", "mps", "apple-silicon",
         "ai", "machine-learning", "terminal", "mlx", "pytorch",
     ],
-)
+)