NVIDIA ships CUDA Python 1.0 with stable APIs, making Python first-class for CUDA
PyTorch · x · 2026-09-09
Alongside CUDA 13.3, NVIDIA released CUDA Python 1.0, establishing Python as a supported, first-class way to use CUDA with semantic versioning. cuda.core 1.0.0 offers a Pythonic runtime interface (devices, streams, green contexts, checkpointing), cuda.compute 1.0.0 exposes CCCL parallel algorithms with Python lambdas, and cuda.bindings 13.3.0 covers CUDA C APIs 1:1. PyTorch, CuPy, and NVIDIA's own libraries now build on the shared cuda.core foundation, reducing version conflicts.
More from Infra
- Google Cloud CEO: TPU servers pay back in ~1 year, half that of GPU servers — matt_slotnick · 2026-09-09
- DeepSeek v4.1 Flash flash sale: 58M tokens for $1, available for 2 days only — MicahBerkley · 2026-09-09
- New top_level_requeue mode for ComfyUI MiniMaxH3 loop stops RAM growth on long video runs — Slight-Living-8098 · 2026-09-09
- Top visitors to a zero-user hobby project: Amazon, Anthropic, OpenAI crawlers — zeeg · 2026-09-09
- Kimi K3 (2.8T) runs at 1 token/s on a MacBook Pro, streamed from four SSDs — Argonautlabs · 2026-09-09
- Inference is turning GPU compute into a tradable commodity — ArtificialAnlys · 2026-09-09