modelsdesk 0.1.0 → 0.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/package.json +1 -1
  2. package/skills/modeldesk/SKILL.md +4 -0
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "modelsdesk",
3
- "version": "0.1.0",
3
+ "version": "0.2.0",
4
4
  "description": "One CLI to find, install, serve, and monitor local LLMs — macOS first, provider-agnostic core.",
5
5
  "license": "GPL-3.0-or-later",
6
6
  "type": "module",
package/skills/modeldesk/SKILL.md CHANGED
@@ -71,6 +71,10 @@ backend install status, RAM estimate vs this machine, and cache state.
71
71
  | `mlx-lm` | MLX | macOS arm64, macOS 14+ | `brew install mlx-lm` |
72
72
  | `llama-cpp` | GGUF (auto-downloaded) | macOS/Linux/Windows | brew / apt / dnf / pacman / winget / choco |
73
73
  | `ollama` | registry names | macOS/Linux/Windows | brew / install script / winget |
74
+ | `strata` | own tiers (q2_0, iq3_s, gyro-s…) | macOS/Linux/Windows | `curl … install.sh \| sh` (Strata) |
75
+ | `mistral-rs` | GGUF + safetensors | macOS/Linux/Windows | `curl … mistralrs.dev/install.sh \| sh` |
76
+ | `vllm` | safetensors/GGUF | Linux/Windows (CUDA) | `pip install vllm` |
77
+ | `sglang` | safetensors/GGUF | Linux (CUDA) | `pip install 'sglang[all]'` |
74
78
 
75
79
  `start`, `setup`, and `doctor --fix` install a missing backend automatically
76
80
  (OS + distro detected at runtime). Minimum versions are gated (mlx-dspark