macfleet 2.0.0__tar.gz

macfleet-2.0.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 MacFleet Contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

macfleet-2.0.0/PKG-INFO

@@ -0,0 +1,175 @@
+Metadata-Version: 2.2
+Name: macfleet
+Version: 2.0.0
+Summary: Pool Apple Silicon Macs into a distributed ML training cluster
+Author: MacFleet Contributors
+License: MIT
+Project-URL: Homepage, https://github.com/vikranthreddimasu/MacFleet
+Project-URL: Documentation, https://github.com/vikranthreddimasu/MacFleet#readme
+Project-URL: Repository, https://github.com/vikranthreddimasu/MacFleet
+Project-URL: Issues, https://github.com/vikranthreddimasu/MacFleet/issues
+Keywords: distributed,machine-learning,apple-silicon,mps,mlx,pytorch,training,gpu-pooling,data-parallel
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: MacOS
+Classifier: Programming Language :: Python :: 3
+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: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: zeroconf>=0.131.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: click>=8.1.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: msgpack>=1.0.0
+Provides-Extra: torch
+Requires-Dist: torch>=2.1.0; extra == "torch"
+Provides-Extra: mlx
+Requires-Dist: mlx>=0.5.0; extra == "mlx"
+Provides-Extra: yaml
+Requires-Dist: pyyaml>=6.0; extra == "yaml"
+Provides-Extra: all
+Requires-Dist: torch>=2.1.0; extra == "all"
+Requires-Dist: mlx>=0.5.0; extra == "all"
+Requires-Dist: pyyaml>=6.0; extra == "all"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.23.0; extra == "dev"
+Requires-Dist: ruff>=0.3.0; extra == "dev"
+Requires-Dist: mypy>=1.8.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
+
+# MacFleet
+
+**Pool Apple Silicon Macs into a distributed ML training cluster.**
+
+Zero-config discovery. N-node scaling. WiFi, Ethernet, or Thunderbolt.
+
+```
+  macfleet join                macfleet join               macfleet join
+ ┌──────────────┐           ┌──────────────┐           ┌──────────────┐
+ │  MacBook Pro  │◄────────►│  MacBook Air  │◄────────►│  Mac Studio   │
+ │  M4 Pro       │  WiFi /  │  M4           │  WiFi /  │  M4 Ultra     │
+ │  16 GPU cores │  ETH /   │  10 GPU cores │  ETH /   │  60 GPU cores │
+ │  48 GB RAM    │  TB4     │  16 GB RAM    │  TB4     │  192 GB RAM   │
+ │  weight: 0.35 │           │  weight: 0.15 │           │  weight: 0.50 │
+ └──────────────┘           └──────────────┘           └──────────────┘
+         ▲                          ▲                          ▲
+         └──────────────────────────┴──────────────────────────┘
+                        Ring AllReduce (gradient sync)
+```
+
+## Features
+
+- **Zero-Config Pooling**: `pip install macfleet && macfleet join` — auto-discovers peers via mDNS/Bonjour
+- **N-Node Scaling**: Ring AllReduce for 2+ nodes (not limited to pairs)
+- **Any Network**: WiFi, Ethernet, and Thunderbolt with adaptive buffer tuning
+- **Dual Engine**: PyTorch+MPS and Apple MLX — pluggable via Engine protocol
+- **Heterogeneous Scheduling**: Weighted batch allocation based on GPU cores + thermal state
+- **Gossip Heartbeat**: Peer-to-peer failure detection, automatic coordinator election
+- **Adaptive Compression**: Bandwidth-aware TopK+FP16 (auto-selects by link type: WiFi=200x, Ethernet=20x, TB4=off)
+- **Framework-Agnostic Core**: Communication layer uses numpy — never imports torch/mlx
+- **Health Monitoring**: Thermal, memory, battery, loss trend — composite health score per node
+- **Rich TUI Dashboard**: Real-time cluster topology, training progress, and warnings
+
+## Quick Start
+
+```bash
+pip install macfleet
+```
+
+### Join the pool
+
+```bash
+# On each Mac:
+macfleet join
+```
+
+### Train a model (Python SDK)
+
+```python
+import macfleet
+
+# PyTorch
+with macfleet.Pool() as pool:
+    pool.train(
+        model=MyModel(),
+        dataset=my_dataset,
+        epochs=10,
+        batch_size=128,
+    )
+
+# MLX (Apple native)
+with macfleet.Pool(engine="mlx") as pool:
+    pool.train(
+        model=mlx_model,
+        dataset=(X, y),
+        epochs=10,
+        loss_fn=my_loss_fn,
+    )
+
+# One-liner
+macfleet.train(model=MyModel(), dataset=ds, epochs=10)
+
+# Decorator
+@macfleet.distributed(engine="torch")
+def my_training():
+    ...
+```
+
+### CLI commands
+
+```bash
+macfleet info       # Local hardware profile
+macfleet status     # Discover pool members on the network
+macfleet diagnose   # System health check (MPS, thermal, network)
+macfleet train      # Demo training on synthetic data
+macfleet bench      # Benchmark compute, network, and allreduce
+```
+
+## Architecture
+
+```
+┌─────────────────────────────────────────────────────────────────┐
+│  CLI: macfleet join | status | train | bench | info | diagnose  │
+│  SDK: macfleet.Pool() | macfleet.train()                        │
+├─────────────────────────────────────────────────────────────────┤
+│  Training: DataParallel | TrainingLoop | WeightedSampler        │
+├─────────────────────────────────────────────────────────────────┤
+│  Engines: TorchEngine (PyTorch+MPS) | MLXEngine (Apple MLX)    │
+├─────────────────────────────────────────────────────────────────┤
+│  Compression: TopK + FP16 + Adaptive pipeline                   │
+├─────────────────────────────────────────────────────────────────┤
+│  Pool: Agent | Registry | Discovery | Scheduler | Heartbeat     │
+├─────────────────────────────────────────────────────────────────┤
+│  Communication: PeerTransport | WireProtocol | Collectives      │
+├─────────────────────────────────────────────────────────────────┤
+│  Monitoring: Thermal | Health | Throughput | Dashboard            │
+└─────────────────────────────────────────────────────────────────┘
+```
+
+## Development
+
+```bash
+git clone https://github.com/yourusername/MacFleet.git
+cd MacFleet
+pip install -e ".[dev]"
+make test          # 268 tests
+make bench         # compute + network + allreduce benchmarks
+make lint          # ruff + mypy
+```
+
+## Requirements
+
+- Python 3.11+
+- macOS with Apple Silicon (M1/M2/M3/M4)
+- PyTorch 2.1+ (for torch engine)
+- MLX 0.5+ (optional, for mlx engine)
+
+## License
+
+MIT

macfleet-2.0.0/README.md

@@ -0,0 +1,130 @@
+# MacFleet
+
+**Pool Apple Silicon Macs into a distributed ML training cluster.**
+
+Zero-config discovery. N-node scaling. WiFi, Ethernet, or Thunderbolt.
+
+```
+  macfleet join                macfleet join               macfleet join
+ ┌──────────────┐           ┌──────────────┐           ┌──────────────┐
+ │  MacBook Pro  │◄────────►│  MacBook Air  │◄────────►│  Mac Studio   │
+ │  M4 Pro       │  WiFi /  │  M4           │  WiFi /  │  M4 Ultra     │
+ │  16 GPU cores │  ETH /   │  10 GPU cores │  ETH /   │  60 GPU cores │
+ │  48 GB RAM    │  TB4     │  16 GB RAM    │  TB4     │  192 GB RAM   │
+ │  weight: 0.35 │           │  weight: 0.15 │           │  weight: 0.50 │
+ └──────────────┘           └──────────────┘           └──────────────┘
+         ▲                          ▲                          ▲
+         └──────────────────────────┴──────────────────────────┘
+                        Ring AllReduce (gradient sync)
+```
+
+## Features
+
+- **Zero-Config Pooling**: `pip install macfleet && macfleet join` — auto-discovers peers via mDNS/Bonjour
+- **N-Node Scaling**: Ring AllReduce for 2+ nodes (not limited to pairs)
+- **Any Network**: WiFi, Ethernet, and Thunderbolt with adaptive buffer tuning
+- **Dual Engine**: PyTorch+MPS and Apple MLX — pluggable via Engine protocol
+- **Heterogeneous Scheduling**: Weighted batch allocation based on GPU cores + thermal state
+- **Gossip Heartbeat**: Peer-to-peer failure detection, automatic coordinator election
+- **Adaptive Compression**: Bandwidth-aware TopK+FP16 (auto-selects by link type: WiFi=200x, Ethernet=20x, TB4=off)
+- **Framework-Agnostic Core**: Communication layer uses numpy — never imports torch/mlx
+- **Health Monitoring**: Thermal, memory, battery, loss trend — composite health score per node
+- **Rich TUI Dashboard**: Real-time cluster topology, training progress, and warnings
+
+## Quick Start
+
+```bash
+pip install macfleet
+```
+
+### Join the pool
+
+```bash
+# On each Mac:
+macfleet join
+```
+
+### Train a model (Python SDK)
+
+```python
+import macfleet
+
+# PyTorch
+with macfleet.Pool() as pool:
+    pool.train(
+        model=MyModel(),
+        dataset=my_dataset,
+        epochs=10,
+        batch_size=128,
+    )
+
+# MLX (Apple native)
+with macfleet.Pool(engine="mlx") as pool:
+    pool.train(
+        model=mlx_model,
+        dataset=(X, y),
+        epochs=10,
+        loss_fn=my_loss_fn,
+    )
+
+# One-liner
+macfleet.train(model=MyModel(), dataset=ds, epochs=10)
+
+# Decorator
+@macfleet.distributed(engine="torch")
+def my_training():
+    ...
+```
+
+### CLI commands
+
+```bash
+macfleet info       # Local hardware profile
+macfleet status     # Discover pool members on the network
+macfleet diagnose   # System health check (MPS, thermal, network)
+macfleet train      # Demo training on synthetic data
+macfleet bench      # Benchmark compute, network, and allreduce
+```
+
+## Architecture
+
+```
+┌─────────────────────────────────────────────────────────────────┐
+│  CLI: macfleet join | status | train | bench | info | diagnose  │
+│  SDK: macfleet.Pool() | macfleet.train()                        │
+├─────────────────────────────────────────────────────────────────┤
+│  Training: DataParallel | TrainingLoop | WeightedSampler        │
+├─────────────────────────────────────────────────────────────────┤
+│  Engines: TorchEngine (PyTorch+MPS) | MLXEngine (Apple MLX)    │
+├─────────────────────────────────────────────────────────────────┤
+│  Compression: TopK + FP16 + Adaptive pipeline                   │
+├─────────────────────────────────────────────────────────────────┤
+│  Pool: Agent | Registry | Discovery | Scheduler | Heartbeat     │
+├─────────────────────────────────────────────────────────────────┤
+│  Communication: PeerTransport | WireProtocol | Collectives      │
+├─────────────────────────────────────────────────────────────────┤
+│  Monitoring: Thermal | Health | Throughput | Dashboard            │
+└─────────────────────────────────────────────────────────────────┘
+```
+
+## Development
+
+```bash
+git clone https://github.com/yourusername/MacFleet.git
+cd MacFleet
+pip install -e ".[dev]"
+make test          # 268 tests
+make bench         # compute + network + allreduce benchmarks
+make lint          # ruff + mypy
+```
+
+## Requirements
+
+- Python 3.11+
+- macOS with Apple Silicon (M1/M2/M3/M4)
+- PyTorch 2.1+ (for torch engine)
+- MLX 0.5+ (optional, for mlx engine)
+
+## License
+
+MIT

macfleet-2.0.0/macfleet/__init__.py

@@ -0,0 +1,46 @@
+"""MacFleet v2: Pool Apple Silicon Macs into a distributed ML training cluster.
+
+Zero-config discovery. Framework-agnostic engines. Adaptive networking.
+
+    pip install macfleet && macfleet join
+"""
+
+import logging
+
+__version__ = "2.0.0"
+
+logging.getLogger(__name__).addHandler(logging.NullHandler())
+
+
+def __getattr__(name: str):
+    """Lazy imports for heavy modules (avoid importing torch/mlx at module load)."""
+    if name == "Pool":
+        from macfleet.sdk.pool import Pool
+        return Pool
+    if name == "train":
+        from macfleet.sdk.train import train
+        return train
+    if name == "distributed":
+        from macfleet.sdk.decorators import distributed
+        return distributed
+    if name == "DataParallel":
+        from macfleet.training.data_parallel import DataParallel
+        return DataParallel
+    if name == "TorchEngine":
+        from macfleet.engines.torch_engine import TorchEngine
+        return TorchEngine
+    if name == "MLXEngine":
+        from macfleet.engines.mlx_engine import MLXEngine
+        return MLXEngine
+    raise AttributeError(f"module 'macfleet' has no attribute {name!r}")
+
+
+__all__ = [
+    "__version__",
+    "Pool",
+    "train",
+    "distributed",
+    "DataParallel",
+    "TorchEngine",
+    "MLXEngine",
+]

macfleet-2.0.0/macfleet/cli/__init__.py

@@ -0,0 +1 @@
+"""CLI interface for MacFleet."""