Hugging Face launches Kernel Hub to distribute compute kernels as first-class artifacts
ariG23498 · x · 2026-10-14
Hugging Face's kernels docs introduce the Kernel Hub: Python libraries and apps can load compute kernels directly from the Hub, where kernels are a first-class repo type with pages surfacing supported hardware and versions.
Design goals:
- Portable: loadable from paths outside PYTHONPATH
- Unique: multiple versions of the same kernel can coexist in one Python process
- Compatible: must support recent Python versions and varied PyTorch builds (CUDA versions, C++ ABIs), plus older C library versions
The project splits into kernel-builder (build, package, distribute) and the loader; available kernels are browsable at huggingface.co/kernels.
More from Infra
- CoreWeave bears flag $11B debt due in 12 months, predict bankruptcy by 2027 — SumitGup · 2026-10-14
- Runner trains LoRA directly on quantized GGUFs — no PyTorch, no FP16 base needed — ZenZombie117 · 2026-10-14
- The AI race belongs to whoever gets enough compute online — Meta and xAI prove it — haider1 · 2026-10-14
- GPUs are going on-prem: owning beats blended cloud at 33% utilization and neoclouds at 66% — AccBalanced · 2026-10-14
- Koboldcpp v1.123 adds support for Qwen Image 2.1 — Fcking_Chuck · 2026-10-14
- Inference Boom Runs Blind: H100 Hours Price from $2.20 to $8.00 with No Utilization Data — AccBalanced · 2026-10-14