Skip to content

CLI upgrades#504

Merged
HenryNdubuaku merged 8 commits intomainfrom
cli/feature-upgrades
Mar 6, 2026
Merged

CLI upgrades#504
HenryNdubuaku merged 8 commits intomainfrom
cli/feature-upgrades

Conversation

@rshemet
Copy link
Copy Markdown
Collaborator

@rshemet rshemet commented Mar 6, 2026

Adding a few features:

1. RAM usage display in cactus run:

You: hey how are you?
Assistant: I am doing well, thank you for asking! How are you? I'm feeling a little bit flexible with my responses.

Could you tell me about your day?

[36 tokens | latency: 0.026s | total: 0.233s | 154 tok/s | RAM: 101.5 MB]

--system flag for custom system prompt in cactus run:

Example: cactus run google/gemma-3-270m-it --system "Speak like Shakespeare"

Image handler in cactus run for VLMs:

cactus-list

List models and see which ones are downloaded using cactus list

Screenshot 2026-03-06 at 3 02 21 PM
  • includes an optional --downloaded flag to list downloaded models only
  • moves model list to a shared model.json so we don't duplicate the logic between this and the publish to HF yml

rshemet added 8 commits March 6, 2026 12:46
- Add `cactus list` to show all supported models grouped by type
- Add `--downloaded` flag to filter to local models only
- Extract model registry from workflow YAML into shared models.json
- Both CLI and publish workflow now read from single source of truth
- Add `quantization=` field to config.txt for accurate precision display
- Green ⬇ indicator, tags, disk size, and quantization for downloaded models

Signed-off-by: Roman Shemet <[email protected]>
@HenryNdubuaku HenryNdubuaku merged commit 687a610 into main Mar 6, 2026
3 of 5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants