chore(deps): update nvidia/cuda docker tag to v13#88
Open
Varashi wants to merge 1 commit into
Open
Conversation
📝 WalkthroughWalkthroughWorker Dockerfile base image updated from CUDA 12.6.3-runtime-ubuntu24.04 to 13.2.1-runtime-ubuntu24.04. Single-line dependency version bump affecting the container runtime layer. ChangesCUDA Base Image Update
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
worker/Dockerfile (1)
13-13:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winStale base-image comment now mismatches effective image tag.
Line 13 still documents
12.6.3-runtime-ubuntu24.04; effective base at Line 33 is13.2.1-runtime-ubuntu24.04. Update comment to avoid operator/debug drift.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@worker/Dockerfile` at line 13, The top-of-file comment documenting the base image is stale (mentions "nvidia/cuda:12.6.3-runtime-ubuntu24.04") and should be updated to match the actual FROM image tag used ("nvidia/cuda:13.2.1-runtime-ubuntu24.04"); edit the comment text that references the base image so it reflects the effective image tag and any descriptor (e.g., "runtime-ubuntu24.04") to avoid operator/debug drift.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@worker/Dockerfile`:
- Line 33: The Dockerfile comment header is stale and CI lacks coverage for CUDA
runtime init after bumping FROM in worker/Dockerfile to
nvidia/cuda:13.2.1-runtime-ubuntu24.04; update the top-of-file header text to
reflect the new base image and add a CI smoke step on a self-hosted GPU runner
(e.g., in build-worker.yaml) that runs a minimal in-container ffmpeg invocation
using -init_hw_device cuda=... plus a CUDA filter such as scale_cuda or
tonemap_cuda and fails on nonzero exit so CUDA hw init is exercised (ensure the
step does not set REPLAY_NO_FFMPEG=1 and add a short docker-compose or docker
run that launches the worker image to execute the ffmpeg command); this will
detect init errors with the new CUDA runtime while keeping existing non-GPU CI
unchanged (docker-compose-smoke.yaml can remain without the worker for GH
runners).
---
Outside diff comments:
In `@worker/Dockerfile`:
- Line 13: The top-of-file comment documenting the base image is stale (mentions
"nvidia/cuda:12.6.3-runtime-ubuntu24.04") and should be updated to match the
actual FROM image tag used ("nvidia/cuda:13.2.1-runtime-ubuntu24.04"); edit the
comment text that references the base image so it reflects the effective image
tag and any descriptor (e.g., "runtime-ubuntu24.04") to avoid operator/debug
drift.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 00245bdc-bfa3-47a4-b8d6-45592c45eb6a
📒 Files selected for processing (1)
worker/Dockerfile
| -o /out/scaleplex-agent ./... | ||
|
|
||
| FROM nvidia/cuda:12.6.3-runtime-ubuntu24.04 | ||
| FROM nvidia/cuda:13.2.1-runtime-ubuntu24.04 |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Read-only repo reconnaissance: verify whether a CUDA/NVENC smoke check already exists.
# Expectation: a workflow/job/script explicitly validates CUDA hw init or NVENC path.
set -euo pipefail
echo "== Search workflows/scripts for CUDA/NVENC smoke checks =="
rg -n -C2 --iglob '*.yml' --iglob '*.yaml' --iglob '*.sh' \
'init_hw_device|hwaccel|nvenc|nvdec|nvidia-smi|NVIDIA_DRIVER_CAPABILITIES|/dev/nvidia0|ffmpeg.*cuda'
echo
echo "== Search Dockerfile/worker docs for declared verification steps =="
rg -n -C2 'cuda|nvenc|nvdec|smoke|validation|compat' worker/Dockerfile worker/ README.mdRepository: Varashi/scaleplex
Length of output: 50374
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== Check CI/workflows for CUDA/NVENC smoke checks =="
if [ -d .github ]; then
rg -n --hidden --glob '!.git/*' \
'(init_hw_device|hwaccel|nvenc|nvdec|nvidia-smi|NVIDIA_DRIVER_CAPABILITIES|/dev/nvidia0|ffmpeg.*cuda)' \
.github/workflows .github/actions .github/scripts 2>/dev/null || true
else
echo "No .github directory"
fi
echo
echo "== Search for nvidia-smi / hwdevice init across repo (trimmed) =="
rg -n --hidden --glob '!.git/*' \
'(nvidia-smi|init_hw_device|filter_hw_device|hwaccel_output_format|tonemap_cuda|scale_cuda)' \
--glob '!worker/agent/testdata/**' --glob '!worker/agent/testdata/*.json' \
--glob '!worker/agent/testdata/**/**.json' .
echo
echo "== Inspect worker/Dockerfile header comments around lines 10-20 =="
nl -ba worker/Dockerfile | sed -n '1,60p'
echo
echo "== Inspect NVENC-related unit tests that mention -init_hw_device =="
rg -n --glob 'worker/agent/*test*.go' \
'init_hw_device|filter_hw_device|scale_cuda|tonemap_cuda' worker/agent | head -n 200Repository: Varashi/scaleplex
Length of output: 50435
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== List common CI entrypoints =="
ls -la .github 2>/dev/null || echo "no .github dir"
ls -la . 2>/dev/null | head -n 200
find . -maxdepth 3 -type f \( -name "*.yml" -o -name "*.yaml" \) \
\( -path "./.github/*" -o -name "Dockerfile" -o -path "./deploy/*" -o -path "./scripts/*" \) 2>/dev/null | head -n 200
echo
echo "== Show GitHub workflows files (if any) =="
if [ -d .github/workflows ]; then
find .github/workflows -type f -maxdepth 2 \( -name "*.yml" -o -name "*.yaml" \) | sed -n '1,200p'
else
echo "no .github/workflows"
fi
echo
echo "== Search workflows/scripts for CUDA/NVENC smoke hooks (GPU runtime check keywords) =="
rg -n --hidden --glob '!.git/*' \
'(nvidia-smi|NVIDIA_DRIVER_CAPABILITIES|/dev/nvidia0|ffmpeg.*cuda|init_hw_device.*cuda|filter_hw_device.*cuda|hwaccel_output_format:0 *cuda)' \
.github/workflows .github/actions .github/scripts 2>/dev/null || true
echo
echo "== Inspect worker/Dockerfile around header + FROM lines =="
sed -n '1,80p' worker/Dockerfile | cat -n | sed -n '1,80p'
echo
echo "== Confirm existing CUDA-related tests (unit vs integration) =="
rg -n --glob 'worker/agent/*test*.go' 'init_hw_device.+cuda|filter_hw_device.+cuda|scale_cuda|tonemap_cuda' worker/agent \
| head -n 200Repository: Varashi/scaleplex
Length of output: 12440
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== Search within workflows for ffmpeg/cuda/nvenc/nvidia keywords =="
rg -n --glob '*.yml' --glob '*.yaml' \
'(ffmpeg.*cuda|init_hw_device|filter_hw_device.*cuda|nvenc|nvdec|nvidia-smi|/dev/nvidia0|NVIDIA_VISIBLE_DEVICES|NVIDIA_DRIVER_CAPABILITIES|hwaccel_output_format:0\s*cuda)' \
.github/workflows
echo
echo "== Inspect docker-compose-smoke workflow (top 200 lines) =="
sed -n '1,220p' .github/workflows/docker-compose-smoke.yaml | cat -n
echo
echo "== Inspect build-worker workflow (top 200 lines) =="
sed -n '1,220p' .github/workflows/build-worker.yaml | cat -n
echo
echo "== Inspect build-ffmpeg workflow (top 220 lines) =="
sed -n '1,220p' .github/workflows/build-ffmpeg.yaml | cat -nRepository: Varashi/scaleplex
Length of output: 129
🏁 Script executed:
#!/bin/bash
set -euo pipefail
for f in \
.github/workflows/docker-compose-smoke.yaml \
.github/workflows/build-worker.yaml \
.github/workflows/build-orchestrator.yaml \
.github/workflows/build-shim.yaml \
.github/workflows/build-ffmpeg.yaml \
.github/workflows/build-ffmpeg-deps.yaml
do
echo "===== $f (line count) ====="
wc -l "$f" || true
echo
echo "===== $f (content) ====="
sed -n '1,260p' "$f" | cat -n
echo
done
echo "== Search for container/GPU smoke signals across workflows (looser patterns) =="
rg -n --glob '*.yml' --glob '*.yaml' \
'(docker\s+compose|compose|up -d|nvidia|NVIDIA|gpu|cud(a|nn)|cuda|nvidia-smi|/dev/nvidia|ffmpeg|ffprobe|smoke|smoketest|smoke-test|hwaccel|nvenc|nvdec)' \
.github/workflowsRepository: Varashi/scaleplex
Length of output: 24574
Add CUDA device-init smoke coverage for the CUDA runtime base bump
FROM nvidia/cuda:13.2.1-runtime-ubuntu24.04- CI currently doesn’t exercise CUDA hw init:
build-worker.yamlruns replay withREPLAY_NO_FFMPEG=1(rewriter-only), anddocker-compose-smoke.yamlomits the worker because GH runners lack GPU passthrough, soffmpeg -init_hw_device cuda=.../ CUDA surface init isn’t hit. - Add a CI step on a self-hosted GPU runner that runs a minimal in-container
ffmpegcommand reaching the CUDA path (e.g. includes-init_hw_device cuda=...and a CUDA filter likescale_cudaortonemap_cuda) and fails on init errors.
Fix stale Dockerfile header base version
worker/Dockerfileheader comment still saysnvidia/cuda:12.6.3-runtime-ubuntu24.04while the image now usesnvidia/cuda:13.2.1-runtime-ubuntu24.04. Update the header text to match.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@worker/Dockerfile` at line 33, The Dockerfile comment header is stale and CI
lacks coverage for CUDA runtime init after bumping FROM in worker/Dockerfile to
nvidia/cuda:13.2.1-runtime-ubuntu24.04; update the top-of-file header text to
reflect the new base image and add a CI smoke step on a self-hosted GPU runner
(e.g., in build-worker.yaml) that runs a minimal in-container ffmpeg invocation
using -init_hw_device cuda=... plus a CUDA filter such as scale_cuda or
tonemap_cuda and fails on nonzero exit so CUDA hw init is exercised (ensure the
step does not set REPLAY_NO_FFMPEG=1 and add a short docker-compose or docker
run that launches the worker image to execute the ffmpeg command); this will
detect init errors with the new CUDA runtime while keeping existing non-GPU CI
unchanged (docker-compose-smoke.yaml can remain without the worker for GH
runners).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR contains the following updates:
12.6.3-runtime-ubuntu24.04→13.2.1-runtime-ubuntu24.04Configuration
📅 Schedule: (UTC)
🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.
♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.
🔕 Ignore: Close this PR and you won't be reminded about this update again.
This PR has been generated by Mend Renovate.