ashim-hq 79c4ed6a35 perf: parallelize model downloads and switch to registry cache ...

- Parallelize all 14 model downloads using ThreadPoolExecutor (6 workers)
  Downloads were sequential (~30 min), now concurrent (~5-10 min)
- Switch Docker cache from type=gha to type=registry (GHCR)
  GHA cache has 10 GB limit causing blob eviction and corrupted builds
  Registry cache has no size limit and persists across runner instances
- Add pip download cache mounts to all pip install layers
  Prevents re-downloading packages when layers rebuild

2026-04-17 14:54:23 +08:00

..

ISSUE_TEMPLATE

chore: rename Stirling-Image to ashim across entire codebase

2026-04-14 20:55:42 +08:00

workflows

perf: parallelize model downloads and switch to registry cache

2026-04-17 14:54:23 +08:00

FUNDING.yml

chore: rename Stirling-Image to ashim across entire codebase

2026-04-14 20:55:42 +08:00

pull_request_template.md

chore: rename Stirling-Image to ashim across entire codebase

2026-04-14 20:55:42 +08:00