Skip to content
QuenchWorks

vllm

Chart · Machine learning & AI · standard · v0.0.5

digest pinnedcosign signedSPDX SBOMSLSA provenanceamd64 · arm64Rebuilt 2026-09-06

vLLM, the high-throughput LLM inference and serving engine with an OpenAI-compatible API. CPU build — installs vLLM's prebuilt CPU wheel (torch+cpu, no source compile, no CUDA) into a venv on a hardened Wolfi python-3.12 base, 0-CVE across ~140 Python packages. The user supplies the model; the chart runs it as a StatefulSet with a persistent model cache.

Version

0.0.5 · latest0.0.40.0.3

The latest line lives at the base page; older lines have their own page so you can pin and verify exactly that version. Only the most recent releases are listed — an older chart pins an older image digest.

Deployed image digest

sha256:cda259cf4c910175e94a19ee23d238ad81f5223871699c8d6f0f2d640ea7816b

Chart OCI version

oci://ghcr.io/quenchworks/charts/vllm:0.0.5

The chart pins its image by this signed digest, so you never track it yourself. Signatures, SBOM, and provenance attach to the same digest.

Signed
cosign keyless
SBOM
SPDX, on image
Provenance
SLSA build
Architectures
amd64, arm64
Runs as
nonroot (uid 1001)
Root filesystem
read-only
Image size
1016.5 MB

Security report (Trivy)

C· 55/1005 fixable · rebuild clears them

Vulnerability detail

vllm 0.27.1 · 5 CVE
CVESeverityPackageInstalledFixed inTitle
CVE-2026-18374MEDIUMglibc-2.442.44-r52.44-r6glibc: glibc: Heap buffer overflow via attacker-controlled fopen mode string
CVE-2026-18374MEDIUMglibc-2.44-locale-posix2.44-r52.44-r6glibc: glibc: Heap buffer overflow via attacker-controlled fopen mode string
CVE-2026-18374MEDIUMld-linux-2.442.44-r52.44-r6glibc: glibc: Heap buffer overflow via attacker-controlled fopen mode string
CVE-2026-18374MEDIUMlibcrypt1-2.442.44-r52.44-r6glibc: glibc: Heap buffer overflow via attacker-controlled fopen mode string
CVE-2026-85091MEDIUMzlib1.3.2-r51.3.3-r0zlib versions 1.3.1.2 through 1.3.2 contain a heap buffer overflow vul ...
0
Critical
0
High
5
Medium
0
Low
0
Unknown

Security report (Trivy) · image vllm 0.27.1

Install the chart

Deploy to Kubernetes with hardened defaults. The chart pins its image by signed digest, so you never track it yourself.

Install (latest)

helm install my-vllm oci://ghcr.io/quenchworks/charts/vllm --version 0.0.5

Deploys image (digest-pinned)

ghcr.io/quenchworks/images/vllm@sha256:cda259cf4c910175e94a19ee23d238ad81f5223871699c8d6f0f2d640ea7816b
Chart version
0.0.5
App version
0.27.1
Chart license
Apache-2.0
App license
Apache-2.0
Service port
8000
Signed
cosign (keyless)
Values schema
yes
Last published
2026-08-27

Verify the chart

cosign verify ghcr.io/quenchworks/charts/vllm:0.0.5 \
  --certificate-identity-regexp 'https://github.com/quenchworks/.+' \
  --certificate-oidc-issuer https://token.actions.githubusercontent.com

Transparency

The chart publishes its attestations on GitHub and the image it deploys carries its own on the same digest, publicly verifiable with the commands above. Both log to the Sigstore transparency log (Rekor), which cosign verify checks for you.

View the imageView on ArtifactHubChart source

Upstream project: https://docs.vllm.ai