Skip to content

Best-Known Configs

A Best-Known Config (BKC) is a curated deployment recipe for a specific model and runtime. It captures the settings that usually require the most trial and error, while leaving the final review editable.

The current source catalog contains 85 vLLM recipes across 80 unique model IDs. It includes model families from NVIDIA, OpenAI, Meta, Google, Mistral, Qwen, DeepSeek, Microsoft, Moonshot AI, Z.ai/GLM, and other publishers.

The catalog is part of the Yokai binary, so recipe changes are versioned and reviewed with the code.

FieldPurpose
ID and nameStable identity and operator-facing label
Workloadvllm or llamacpp catalog type
Model IDExact Hugging Face repository
ImageTested runtime image or vendor build
PortDefault service port
Extra argumentsParser, quantization, parallelism, context, or feature flags
Environment and volumesRuntime inputs and mounted assets
PluginsModel-specific assets and flags
RuntimeIPC, shared memory, and ulimits
Target devicesExplicitly validated GPU profiles
Minimum resourcesVRAM per GPU and GPU-count requirements
Quantization and architectureMatching and operator context
Source and notesProvenance and important constraints

When several recipes target one model, Yokai prefers the most specific entry that names the selected device profile. It then considers minimum GPU count and VRAM. If no exact hardware profile matches, it returns the first resource-compatible recipe and exposes the choice for review.

Supported profile tags include GB10, Jetson Thor, RTX PRO 6000, RTX 5090, RTX 4090, L40S, A100, H100/H100 NVL, H200, H20, B200, GB200, MI300X, MI325X, MI355X, and Radeon AI PRO R9700.

  • Exact: workload and model repository match a catalog entry.
  • Suggested: Yokai normalizes the repository owner and model tokens, then ranks a close catalog entry from the same owner.

Always inspect a suggested match before deployment. Similar names do not guarantee identical architecture or runtime requirements.

In the Deploy route, select the model and press B during configuration. Yokai fills the tested values, but you can still change the image, port, flags, GPUs, environment, volumes, plugins, or runtime options before review.

Some models need assets that are not built into the base runtime image. A BKC can reference a Yokai plugin that downloads those assets, mounts them into the container, and appends the required flags. Plugin assets are stored under ~/.local/share/yokai/plugins by default, /var/lib/yokai/plugins for root, or $YOKAI_PLUGIN_DIR when set.

BKC entries live in internal/bkc/catalog_*.go. A useful contribution includes:

  • the exact model and image versions tested;
  • hardware profile, GPU count, and VRAM requirement;
  • all runtime flags and environment variables;
  • a source link and notes about known constraints;
  • tests for lookup and device matching when the entry adds a new edge case.