Add nvidia-vss-vllm 3.2.2 (NVIDIA VSS Blueprint 3.1.0)#242
Open
blik616287 wants to merge 6 commits into
Open
Conversation
![bulwark-spectrocloud[bot]](https://avatars.githubusercontent.com/u/36211249?s=60&v=4){kind=small}
There was a problem hiding this comment.
✅ CVE scan completed successfully.
Scan Summary:
- Total images scanned: 4
- Clean images: 2
- Images with CVEs: 2
- Total CVEs found: 219
🔴 Critical CVEs: 5
🟠 High CVEs: 28
🟡 Medium CVEs: 21
🟢 Low CVEs: 165
Images with CVEs:
- docker.io/alpine/curl:8.12.1: 82 CVEs (Critical: 2, High: 7, Medium: 3, Low: 70)
Critical CVEs: CVE-2026-31789 - nginx:1.27-alpine: 137 CVEs (Critical: 3, High: 21, Medium: 18, Low: 95)
Critical CVEs: CVE-2025-48174, CVE-2026-31789
Pack references only public 0/0 Chainguard images (wolfi-base/nginx/curl). The gated NVIDIA vLLM runtime is fetched as data at deploy (crane export, NGC creds) and run non-privileged on wolfi-base via rootfs-linker swap + gcc/g++ --sysroot wrappers + CUDA tool paths. Validated on a GB10 (Blackwell arm64): serves nemotron, HTTP 200. content.images all public 0/0; validator content check passes (no gated pull). The running container carries NVIDIA CUDA-stack CVEs as runtime data, not in the scanned pack image. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
3.2.2 validated running 2/2 on a GB10 edge cluster. Merged upstream/main (crane-manifest validator fix). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
blik616287
changed the title
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
nvidia-vss-vllm — VSS 3.x, pack
3.1.4VSS 3.x standalone vLLM LLM backend (
nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8) as a Helm chart, fronted by an nginx sidecar (llm-nim-svc).gpuMemUtil: 0.4— sized so the LLM co-resides with the Cosmos VLM on a single GB10 (119.6 GiB unified); raise it on a dedicated GPU.Versioning: chart/pack
version: 3.1.4(our packaging) ·appVersion: 3.1.0(upstream NVIDIA VSS Blueprint 3.x). Helm chart; images pinned invalues.yamlpack.content.images.Tested on NVIDIA GB10 / DGX Spark (arm64 SBSA)
Deployed via Palette add-on cluster profile
vss-dgx-spark-3xon edge clusteredge-gx10(single GB10). Full VSS 3.x route green — all 5 packs reportPack services are ready, cluster Running:Validation:
pack.jsonJSON-syntax/schema/version, logo, README, andpack.content.imagesall pass. Thecontent.imagespull (crane) fails for the gatednvcr.io/nim/*andnvcr.io/nvidia/vss-core/*images — the CI runner has no NGC credentials (same image-pull exception as the 2.4 PRs #233–236; the cluster pulls them viangc-pull-secret).