Files
hermes-agent/website
teknium1 2e6924bd10 fix(local-runtime): size AMD/Intel GPUs by the engine's own device type
The previous commit budgets any Vulkan/HIP device that `llama-server
--list-devices` prints as a discrete card. That output carries no
integrated-vs-discrete verdict, so an iGPU (Intel ADL-N reports 11.8 GB of
a 16 GB machine's shared memory) would be counted twice: once as VRAM and
again as system-RAM spill.

Ask the installed engine's ggml library instead, in a bounded child
process: ggml_backend_dev_type() is GPU for a discrete card and IGPU for
an integrated one (Vulkan reads it from VkPhysicalDeviceType). llama.cpp
places layers on discrete devices whenever one exists and falls back to an
integrated GPU only otherwise, so the budget follows the same rule:

- discrete device -> its own memory, system RAM as spill (uma=False)
- integrated GPU, no answer, CPU/Metal -> RAM-as-unified, unchanged

The probe runs only when no NVIDIA device answered and the configured
engine is Vulkan/HIP, and is cached per engine binary (the hardware
endpoint polls every few seconds). The CUDA --list-devices fallback for the
NVIDIA unified-pool quirk is left as it was on main.

Co-authored-by: Belaquaa <eee_pokkk@mail.ru>
2026-10-03 02:25:26 -07:00
..
2026-10-02 17:52:02 -04:00
…

Website

This website is built using Docusaurus, a modern static website generator.

Reading the docs on GitHub? The Markdown under docs/ is authored for the rendered site at https://hermes-agent.nousresearch.com/docs/. Cross-page links are relative Markdown paths, so they follow through on GitHub's file viewer too. Every page on the site has an Edit this page link that opens the source file here.

  • Link to another page with a relative Markdown path, anchors included: [Profiles](../user-guide/profiles.md), [Bundles](../user-guide/features/skills.md#skill-bundles). Docusaurus turns the file path into the page route; GitHub follows the same path. Site routes (/user-guide/profiles, /docs/user-guide/profiles) only work on the rendered site — GitHub resolves them as repository paths and 404s, and the /docs/ form also emits /docs/zh-Hans/docs/... 404s in the zh-Hans build because baseUrl is already /docs/.
  • python3 website/scripts/check_doc_links.py fails on any route-style link in hand-authored pages (EN and the zh-Hans mirror); --fix rewrites them. It runs in the Docs Site Checks workflow. Generated pages (user-guide/skills/{bundled,optional}, reference/*skills-catalog.md) are produced by scripts/generate-skill-docs.py, which emits the same relative form.
  • Pin {#anchor} on cross-linked headings so the zh-Hans mirror keeps the same id.

Installation

yarn

Local Development

yarn start

This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.

Build

yarn build

This command generates static content into the build directory and can be served using any static contents hosting service.

Deployment

Using SSH:

USE_SSH=true yarn deploy

Not using SSH:

GIT_USER=<Your GitHub username> yarn deploy

If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the gh-pages branch.

Diagram Linting

CI runs ascii-guard to lint docs for ASCII box diagrams. Use Mermaid (````mermaid`) or plain lists/tables instead of ASCII boxes to avoid CI failures.