Match the project to your task before installing it.
Software Development & Delivery · Public
kernels
Build compute kernels and load them from the Hub.
Check whether this project matches your task before installing it.
What it can doskill, recipe, host_instruction, eval, preflightReview the portable capability path.
Before continuingVerify in a sandboxDo not treat a preview pack as a proven local install.
GitHub snapshot692 stars105 forks · 34 contributors
Doramagic.ai Last verification date: 2026-06-17 Verification method: source evidence, semantic profile, public page gate, and static build acceptance.
Publication status · 2026-06-17
What is kernels?
- Build compute kernels and load them from the Hub.
- Best fit: Users who want source-backed project understanding before installing it.
- Not for: Not for users who want to skip sandbox verification or cannot accept configuration, permission, or maintenance overhead.
- Capability added to an AI workflow: skill, recipe, host_instruction, eval, preflight
- First safe verification step: Verify the smallest path in an isolated environment and keep a rollback path.
- Verification state: source, Quick Start, and sandbox install checks are recorded as passed.
- Top risk: May increase setup, validation, or first-run risk for the user.
- Evidence base: https://github.com/huggingface/kernels, https://github.com/huggingface/kernels#readme, Human Manual, Pitfall Log
01
Quick decision
Use this section to decide whether the project is worth a deeper read.Build compute kernels and load them from the Hub.
692 stars · 105 forks
02
What it can do
Translate the upstream project into concrete capabilities the user can judge before installing.Project Overview and System Architecture
Related topics: Loading Kernels with the kernels Python Package, Building Kernels with kernel-builder and the Nix Builder, Example Kernels and Backend Variants
Source: https://github.com/huggingface/kernels / Human Manual
Loading Kernels with the `kernels` Python Package
Related topics: Project Overview and System Architecture, Building Kernels with kernel-builder and the Nix Builder, Example Kernels and Backend Variants
Source: https://github.com/huggingface/kernels / Human Manual
Building Kernels with `kernel-builder` and the Nix Builder
Related topics: Project Overview and System Architecture, Loading Kernels with the kernels Python Package, Example Kernels and Backend Variants
Source: https://github.com/huggingface/kernels / Human Manual
Example Kernels and Backend Variants
Related topics: Project Overview and System Architecture, Loading Kernels with the kernels Python Package, Building Kernels with kernel-builder and the Nix Builder
Source: https://github.com/huggingface/kernels / Human Manual
Doramagic Pitfall Log
Source-linked risks stay visible on the manual page so the preview does not read like a recommendation.
Source: Doramagic discovery, validation, and Project Pack records
Sources: https://github.com/huggingface/kernels, Human Manual, Project Pack evidence, and downstream validation signals.
03
Community Discussion Evidence
Project-level external discussion stays visible on the detail page, not only inside the manual.Community Discussion Evidence
12 source-linked itemsReview these external discussions before using kernels with real data or production workflows. They are review inputs, not standalone proof that the project is production-ready.
-
01
Push security analysis reports on the Hub for kernels-community kernel r
github / github_issue
-
02
Guide users without kernel publishing access to open a discussion on ker
github / github_issue
-
03
Signal when a kernel build comes from an uncommitted (dirty) kernel-buil
github / github_issue
-
04
v0.15.2
github / github_release
-
05
v0.15.1
github / github_release
-
06
v0.14.1
github / github_release
-
07
v0.14.0
github / github_release
-
08
v0.14.0.dev1
github / github_release
-
09
v0.14.0.dev0
github / github_release
-
10
v0.13.0
github / github_release
-
11
v0.12.3
github / github_release
-
12
v0.12.2
github / github_release
04
How to start
Only source-backed commands are shown here. Verify them in an isolated environment first.Try the prompt first
Test the workflow without installing the upstream project.
previewRead the Human Manual
Understand inputs, outputs, limits, and failure modes.
manualTake context to your AI host
Use the compiled assets in your preferred AI environment.
contextRun sandbox verification
Confirm install commands and rollback before using a primary environment.
verifypip install kernelsOfficial start command · https://github.com/huggingface/kernels#readme · verified: yes
05
Human Manual
The English page must expose the real manual, not a short placeholder.8+ sections · Human Manual
kernels Manual
Build compute kernels and load them from the Hub.
Open the full manual- https://github.com/huggingface/kernels Project Manual
- Table of Contents
- Project Overview and System Architecture
- Related Pages
- High-Level Architecture
- Build System: `kernel-builder`
- `build.toml` and kernel identification
- Per-backend templates
Project Overview and System Architecture
Related topics: Loading Kernels with the kernels Python Package, Building Kernels with kernel-builder and the Nix Builder, Example Kernels and Backend Variants
Source: https://github.com/huggingface/kernels / Human Manual
Loading Kernels with the `kernels` Python Package
Related topics: Project Overview and System Architecture, Building Kernels with kernel-builder and the Nix Builder, Example Kernels and Backend Variants
Source: https://github.com/huggingface/kernels / Human Manual
Building Kernels with `kernel-builder` and the Nix Builder
Related topics: Project Overview and System Architecture, Loading Kernels with the kernels Python Package, Example Kernels and Backend Variants
Source: https://github.com/huggingface/kernels / Human Manual
Example Kernels and Backend Variants
Related topics: Project Overview and System Architecture, Loading Kernels with the kernels Python Package, Building Kernels with kernel-builder and the Nix Builder
Source: https://github.com/huggingface/kernels / Human Manual
Doramagic Pitfall Log
Source-linked risks stay visible on the manual page so the preview does not read like a recommendation.
Source: Doramagic discovery, validation, and Project Pack records
06
AI Context Pack and portable assets
After deciding to continue, take the project context into your own AI host.Complete pack plus user-owned assets
These files are planning and verification assets for Claude Code, Codex, Gemini, Cursor, ChatGPT, and other AI hosts.
07
Preflight checks
Treat this page as a planning asset, not proof that your local environment is ready.- The manual is generated from source-linked project files and Doramagic validation signals.
- Community evidence warnings stay visible instead of being converted into marketing claims.
- This English page is indexable because the locale quality gate passed and explicit English index approval is enabled.
- Use the upstream repository as the final authority for installation commands, license, and version-specific behavior.
08
Pitfall Log and verification risks
Doramagic surfaces high-risk items before users treat a candidate capability as verified.Installation risk requires verification
May increase setup, validation, or first-run risk for the user.
Installation risk requires verification
May increase setup, validation, or first-run risk for the user.
Capability evidence risk requires verification
May increase setup, validation, or first-run risk for the user.
Maintenance risk requires verification
May increase setup, validation, or first-run risk for the user.
Security or permission risk requires verification
May increase setup, validation, or first-run risk for the user.
Security or permission risk requires verification
May increase setup, validation, or first-run risk for the user.
Security or permission risk requires verification
May increase setup, validation, or first-run risk for the user.
Maintenance risk requires verification
May increase setup, validation, or first-run risk for the user.