Skip to content

Stretch: evaluate spare GPU headroom for a local vision-language model in visual-review #4335

Description

@JSONbored

Part of #4325.

Non-blocking — explicitly does not gate any other sub-issue or the cutover itself.

Context

The GPU sized for the RAG embedding workload has substantial headroom beyond what the current embedding model needs. The visual-review pipeline's AI-vision analysis step is a plausible candidate to move from a cloud call to a local vision-language model running on this same spare capacity — but this is a genuine quality/cost tradeoff that needs real evaluation, not an assumed win.

Requirements

  • Identify 1-2 candidate open vision-language models that fit comfortably in the available VRAM alongside the embedding model running concurrently.
  • Run the same set of PR screenshots through both the current cloud-based analysis and the candidate local model, and compare output quality side by side — this issue should produce a quality comparison, not just a "it runs" confirmation.
  • Explicitly weigh latency and quality against the cloud path's cost — a local model that's meaningfully worse should be rejected here, not shipped because the hardware happened to be available.

Deliverables

  • Candidate model(s) selected and running locally via Ollama
  • Side-by-side quality comparison against the current cloud-based analysis on a real sample of past PR screenshots
  • Written recommendation: adopt, or explicitly reject with reasoning
  • If adopted: a separate follow-up issue is filed for the actual integration work (out of scope here)

Expected outcome

A data-backed answer to whether the spare GPU capacity is worth using for visual-review analysis — and if not, that's a complete, successful outcome for this issue, not a failure.

Effort

M

Metadata

Metadata

Assignees

Labels

maintainer-onlyOwner-only work — yields no Gittensor points.

Projects

Status
Done

Relationships

None yet

Development

No branches or pull requests

Issue actions