updated 2026-10-17 20:06 UTC

vLLM

Repository Website

A high-throughput and memory-efficient inference and serving engine for LLMs

LLM Gateways & Infra Python Listed Apache-2.0

Is vLLM safe? Strong public trust posture, backed by multiple independent signals.

OSSF Scorecard 6.6 / 10
Provenance None
Signed commits 100%
Last push today
Advisories None known
Compare vLLM

How does it stack up against its LLM Gateways & Infra neighbours?

Pick any agent to compare →
Suggest a correction

In detail: vLLM scores 81.0/100 (Grade A), ranked #150 of 1378 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 6.6/10; 100% of recent commits are signed; no published advisory affects its latest release (vllm); last pushed 2026-10-17. Every point is earned from checkable signals — never paid placement. How scoring works →

How vLLM could raise its score

Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.

Already done? Suggest a correctionAdd the trust badge

Chain of custody

Scanners check what the code says. This traces who ships vLLM and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.

  1. Source Signed

    github.com/vllm-project/vllm, Apache-2.0, last pushed 2026-10-17. 100% of the last 100 commits carry a verified signature, so changes trace to a verified account.

  2. Review and release Mixed

    OpenSSF Scorecard rates the repository's practices 6.6/10 (scanned Oct 11, 2026). The checks that decide who can get a change released:

    • Code Review10
    • Branch Protection4
    • Signed Releases0
    • Dangerous Workflow10
    • Token Permissions9
    • Pinned Dependencies0
    All 18 Scorecard checks
    Binary-Artifacts 10
    Branch-Protection 4
    CI-Tests 10
    CII-Best-Practices 5
    Code-Review 10
    Contributors 10
    Dangerous-Workflow 10
    Dependency-Update-Tool 10
    Fuzzing 0
    License 10
    Maintained 10
    Packaging 10
    Pinned-Dependencies 0
    SAST 1
    Security-Policy 10
    Signed-Releases 0
    Token-Permissions 9
    Vulnerabilities 0

  3. Published packages Linked, not attested

    • PyPI vllm Source link points back to this repo No build attestation

    Without a build attestation, nothing proves the published files were built from this repository.

  4. What you install today No known advisories

    Latest release checked: vllm 0.31.0. No published advisory affects it (OSV, checked 2026-10-17).

Changes to this chain

No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of vLLM.

Evidence behind this score

Coverage A: 4 of 5 independent evidence types found.

  • GitHub repository data
  • Package downloads
  • Supply-chain checks
  • Public actions (missing)
  • Community mentions

Verify this score yourself

Every build re-issues vLLM’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.

Signed credential (JSON) How to verify

What this score doesn’t check

It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.

How vLLM compares in LLM Gateways & Infra

  1. #1 Bifrost 90.3 +9.3
  2. #2 Headroom 89.4 +8.4
  3. #3 vLLM 81.0 this agent
  4. #4 LiteLLM 78.3 −2.7
  5. #5 Ollama 66.4 −14.6

Bars show each HVTrust score; the tick marks vLLM’s 81.0.

Where the 81.0 comes from

HVTrust dimensions vs the LLM Gateways & Infra average

81.0 / 100 · 100.0% confidence

vLLM LLM Gateways & Infra average (14 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
13.2 / 25
2.8 above avg 10.4
Identity / Provenance60% listing status · 40% build provenance
10.8 / 18
1.0 below avg 11.8
Transparency50% declared license · 50% OSSF Scorecard
14.1 / 17
1.4 above avg 12.7
Maintenance60% last-push freshness · 40% commit activity
20.0 / 20
3.5 above avg 16.5
AdoptionLog-scaled stars · package downloads
19.5 / 20
6.1 above avg 13.4

Quick Trust Read

What Would Improve It
Publish package provenance or release attestations for stronger supply-chain evidence.
Recent Changes
2026-09-23
Rank Moved
Rank dropped 62 spots (#67 → #129)
2026-09-21
Rank Moved
Rank rose 59 spots (#126 → #67)
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 6.6/10. Tighten the weakest checks to improve public safety evidence.
Publish provenance Add package provenance or release attestations so users can verify where shipped artifacts came from.
Compare with Bifrost Get email alerts for vLLM View LLM Gateways & Infra Report missing data
99.8
Activity sub-score · out of 100
#3
In LLM Gateways & Infra

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade A reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage A is separate — it grades how many independent signal types back the score (4 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-10-17 20:06 UTC · Repo last pushed today

Rank Trend

2026-09-29 2026-10-17

Activity & Reach

Stars
94.0k
Forks
23.5k
Last Push
2026-10-17
today
Commits (4 wk)
1727
Downloads (7d)
479,505
pypi
HN mentions (30d)
844
Open Issues
2649
Rank Change
=
was #150

Analysis

Activity Inputs

99.8 / 100
StarsRepository reach
29.8 / 30
FreshnessLast push recency
25.0 / 25
ActivityRecent commits
25 / 25
CommunityFork signal
20 / 20

Common questions about vLLM

Public supply-chain signals for vLLM are strong: it has multiple independent trust indicators in place. This does not replace your own security review, but vLLM carries less obvious unverified-evidence risk than projects with thin signals.
Does vLLM publish package provenance?
No published build provenance is currently detected for vLLM. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does vLLM have an OpenSSF Scorecard?
vLLM has an OpenSSF Scorecard score of 6.6/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.
Is vLLM actively maintained?
Actively maintained. The repository was pushed to within the last 1 day(s).
What license does vLLM use?
vLLM ships under Apache-2.0. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are vLLM's commits signed?
100% of the last 100 commits to vLLM are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.

Compare vLLM head-to-head

vLLM vs Bifrost → vLLM vs Headroom → vLLM vs LiteLLM →

AI agent surface

MCP, providers, tool surface
Scored in HVTrust

These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →

MCP Server Support
medium confidence
Declared
MCP support appears present, but direct server implementation is less certain.
Detailed evidence is not shown in the public view.
External Service Dependencies
None detected
No clear third-party provider dependency detected.
Credential signal: No explicit API-key/config marker detected.
Tool / Plugin Surface
high confidence
Extensions
Extension based plugin/integration surface detected.
Detailed evidence is not shown in the public view.
Package Provenance Drift
high confidence
Match
Published package metadata matches the tracked repo
Detailed evidence is not shown in the public view.
  • MCP signal live
  • External deps live
  • Tool / plugin surface live
  • Package provenance drift live

Maintain vLLM?

For maintainers

HVTrust scores vLLM from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history
Rank 3Grade 1
2026-09-23
Rank Moved
Rank dropped 62 spots (#67 → #129)
2026-09-21
Rank Moved
Rank rose 59 spots (#126 → #67)
2026-09-05
Rank Moved
Rank dropped 24 spots (#85 → #109)
2026-07-21
Grade Changed
Trust grade A → B
GitHub → Website → PyPI: vllm

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 81.0 Grade A
Markdown:
[![HVTrust](https://hvtracker.net/badge/vllm.svg)](https://hvtracker.net/agents/vllm)
HTML:
<a href="https://hvtracker.net/agents/vllm"><img src="https://hvtracker.net/badge/vllm.svg" alt="HVTrust"></a>

Other agents in LLM Gateways & Infra

Data sources
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI · Algolia HN Search API
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON