fix(agent): cuDNN base image so onnxruntime-gpu loads #146

Merged

bvandeusen merged 2 commits from dev into main 2026-06-29 18:48:25 -04:00

Conversation 0 Commits 2 Files Changed 2

+44 -2

bvandeusen commented 2026-06-29 18:48:06 -04:00

Owner

Copy Link

Copy Source

First-run fix: the agent's CUDA execution provider failed with libcudnn.so.9: cannot open shared object file — onnxruntime-gpu needs cuDNN 9, which the plain cuda:12.4.1-runtime image lacks. Switch the agent base to cuda:12.4.1-cudnn-runtime-ubuntu22.04. Triggers a build-agent republish; operator re-pulls.

🤖 Generated with Claude Code

First-run fix: the agent's CUDA execution provider failed with `libcudnn.so.9: cannot open shared object file` — onnxruntime-gpu needs cuDNN 9, which the plain `cuda:12.4.1-runtime` image lacks. Switch the agent base to `cuda:12.4.1-cudnn-runtime-ubuntu22.04`. Triggers a `build-agent` republish; operator re-pulls. 🤖 Generated with [Claude Code](https://claude.com/claude-code)

bvandeusen added 2 commits 2026-06-29 18:48:06 -04:00

docs(agent): docker-compose for the GPU agent ... b6b151a500

compose file (pull the published image, GPU reservation, model-cache volume,
.env for the token) so the agent runs with `docker compose up -d` instead of a
long docker run. A copy + .env template also placed in ~/Documents/fc-gpu-agent.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa

fix(agent): cuDNN base image so onnxruntime-gpu loads (#114) ... 7b10f4caab

onnxruntime-gpu needs cuDNN 9; the plain cuda:12.4.1-runtime image lacks it
(libcudnn.so.9 missing → CUDAExecutionProvider falls back to CPU). Switch to
the -cudnn-runtime variant which bundles cuDNN 9.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa

bvandeusen merged commit d52ac0a0e2 into main 2026-06-29 18:48:25 -04:00

bvandeusen referenced this issue from a commit 2026-07-07 20:03:23 -04:00

feat(translation): re-translate on model change — artist-scoped + global re-run (#146)

Sign in to join this conversation.

Reviewers

No Reviewers

Labels

No items

No Label

Milestone

No items

No Milestone

Projects

Clear projects

No project

Assignees

Clear assignees

bvandeusen

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: bvandeusen/FabledCurator#146