metal-graph 0.1.0: A New Python Library for GPU-Accelerated Graph Analytics on Apple Silicon Macs
nischay_twt · x · 2026-07-31
tabulai released metal-graph 0.1.0, a Python library for fast graph analytics on Apple Silicon Macs. It combines a familiar Python interface with optimized native CPU code and GPU acceleration via Apple's Metal framework.
Key features:
- Immutable graph structures with external node ID support
- Optimized CPU and Metal execution paths
- Built specifically for arm64 Macs
- Algorithms: full-vector PageRank, batched personalized PageRank with top-k, multi-source direction-optimizing BFS, k-hop neighborhood extraction, experimental weakly connected components
Install with: pip install metal-graph
More from Infra
- Report: DeepSeek Building 1GW Data Center in Inner Mongolia, Raised $7B — ns123abc · 2026-07-31
- Pig Waste Powers AI: UK Farm Biogas Compute Yields 10x Grid Income — bittingthembits · 2026-07-31
- OpenAI's GPT-5.6 Self-Optimizes: Slashes Serving Costs by 20% — tszzl · 2026-07-31
- Fixing CUDA Conflicts: Pre-built Python Wheels via PyTorch-Style Indexes — charliermarsh · 2026-07-31
- Astral Open-Sources Pre-built GPU Wheels to Fix CUDA/PyTorch Dependency Hell — charliermarsh · 2026-07-31
- Arm Revenue Jumps 22% as Data Center Neoverses Shipments Double — ryanshrout · 2026-07-31