The CPU image was 11.2GB — larger than the CUDA one — and its single 6.72GB
torch layer could not be pushed at all: the registry drops any blob upload
taking longer than 60s, and that layer needed ~61s.
Both problems came from install ordering. Dockerfile.cpu installed the project
and sentence-transformers first, which resolved the default CUDA torch and
pulled ~2.7GB of nvidia-* wheels, then reinstalled torch from the CPU index.
Reinstalling replaces torch but leaves its transitive CUDA dependencies behind,
orphaned and unused (torch reports 2.13.0+cpu, cuda.is_available() False).
Installing CPU torch first, from the CPU index, means nothing ever requests a
CUDA build. Everything else then resolves against the torch already present.
CPU image 11.2GB -> 3.43GB
largest layer 6.72GB -> 896MB
push failed 5/5 at 60s -> succeeds in 8.6s
Dockerfile.nvidia gets the same split. Its torch layer is unavoidably large
(~2.8GiB compressed, ~52s at current throughput) so it stays the tightest
thing in the stack, but splitting the application install off keeps that layer
cached and the app layer small.
Both now install torch before the source COPYs, so editing application code no
longer invalidates the multi-GB layer.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
- Add Dockerfile.cpu and compose.cpu.yaml for CPU-only deployments
- Use sentence-transformers[onnx] + CPU-only torch for ~4x smaller image
- Fix release script: separate git tags (engine-v*) from Docker tags (v*)
- Add CPU image to release build/push pipeline
- Update README with CPU deployment instructions
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
steve