fix: Bump Qwen3-VL-32B-FP8 Hugging Face Hub Pin to Restore hf download

[weizhoublue]

Overview:

Details:

The Qwen3-VL-32B-FP8 model-cache job still installed huggingface_hub==1.11.0 before running hf download, while the other sibling model-cache jobs had already been bumped to huggingface_hub==1.16.4

The specific reason was clarified in PR #10986, which miss fixing for Qwen3-VL-32B-FP8

Where should the reviewer start?

Related Issues

⚠️ This section is required. Choose one path below and delete the other.

🔗 This PR is linked to an issue:

• Closes #XXXX

🚫 This PR is NOT linked to an issue:

• Confirmed — no related issue

Summary by CodeRabbit

• Chores
  • Updated the Hugging Face client used during model download jobs to a newer version.

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[datadog-official]

⚠️ Warnings

🚦 1 Pipeline job failed

PR Reminder Full CI Comment Bot | pr_reminder     

_{This comment will be updated automatically if new data arrives.
🔗 Commit SHA: b7fdfa5 | Docs | Give us feedback!}

[weizhoublue]

@MatejKosec , I think you may miss the fix for Qwen3-VL-32B-FP8 .
thanks and please help review

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 968cb68f-0ddf-4b7f-993b-611e12504b23

📥 Commits

Reviewing files that changed from the base of the PR and between fb08499 and b7fdfa5.

📒 Files selected for processing (1)

• recipes/qwen3-vl-32b-fp8/model-cache/model-download.yaml

---

Walkthrough

The pull request updates a Kubernetes Job manifest for the model-download recipe, changing the pinned huggingface_hub package version from 1.11.0 to 1.16.4 in the container's dependency installation step.

Changes

Dependency version update

Layer / File(s)	Summary
huggingface_hub version pin recipes/qwen3-vl-32b-fp8/model-cache/model-download.yaml	Updated the pinned huggingface_hub version from 1.11.0 to 1.16.4 in the Job container's dependency installation before the hf download command.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Related issues: None provided in the diff context.

Related PRs: None provided in the diff context.

Suggested labels: dependencies, recipes

Suggested reviewers: None specified.

🐰 A tiny hop, a version bump so bright,
huggingface_hub climbs higher tonight,
from eleven to sixteen, the number grows,
in the model-download job, quietly it flows.

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description leaves required template sections as placeholders, including Overview, reviewer start, and Related Issues.	Fill in the Overview and reviewer-start sections, and replace the Related Issues placeholder with the real issue link or explicit no-issue confirmation.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly states the main change: bumping the Qwen3-VL-32B-FP8 Hugging Face Hub pin to restore hf download.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

---

_{Comment @coderabbitai help to get the list of available commands.}