gpusnap warm/snapshot pause hook

[mbrostami]

What

Adds Runner.gpusnap_warm_pause() to the worker lifecycle so a Sprocket worker can be snapshotted warm by gpusnap and restored fast on scale-up (background/queue workers included).

In lifespan, right after setup() + maybe_run_warmup() and before the queue worker starts / /health goes green:

• If GPUSNAP_WARM=<dir> is set (only while gpusnap builds a snapshot), the worker writes <dir>/WARM_READY and blocks until restored + <dir>/RESUME.
• Unset on a normal boot ⇒ no-op, behaviour unchanged.

Why

gpusnap must capture the worker after the model is loaded + JIT-warm but before it claims a real job, or a snapshot would swallow (and lose) a job. This hook is that clean pause point; on restore the worker resumes straight into serving. Works for queue mode, HTTP mode, and TorchRun (multi-GPU) workers.

Pairs with the gpusnap restore.sh RESUME signal and federated-applications#252 (the injecting PodSpecMutator). Full contract: gpusnap deploy/SPROCKET.md.

🤖 Generated with Claude Code

[broly-code-security-scanner]

Broly Security Scan

Note

Baseline snapshot is missing for this repo. Broly is running in PR-only fallback mode until the first scheduled baseline completes. This does not block the PR.

Warning

⚠️ Potential results — Broly is still completing analysis or verification. This comment will update automatically.
Files pending AI analysis: 1; findings pending verification: 0.

Note

Re-scan this PR anytime with /broly scan — useful after /broly undismiss, or to refresh findings without a new push.

Broly — SAST (zai-org/GLM-5.3-Flash) · Secrets · SCA · IaC · GH Actions · Base Images · Supply Chain Threats · Exploit Chains · Adversarial Verification

We're continuously improving Broly's accuracy and finding quality — your feedback is valuable. False positives, missed findings, bugs, and feature requests all welcome.

 

[github-advanced-security]

You are seeing this message because GitHub Code Scanning has recently been set up for this repository, or this pull request contains the workflow file for the Code Scanning tool.

What Enabling Code Scanning Means:

• The 'Security' tab will display more code scanning analysis results (e.g., for the default branch).
• Depending on your configuration and choice of analysis tool, future pull requests will be annotated with code scanning analysis results.
• You will be able to see the analysis results for the pull request's branch on this overview once the scans have completed and the checks have passed.

For more information about GitHub Code Scanning, check out the documentation.