7.1

CVE-2026-55514: vllm-project vllm Reachable Assertion

CVSS: 7.1v4.0HighAnalyzed
AliasesGHSA-33cg-gxv8-3p8gPYSEC-2026-2303CGA-76fr-64w2-fwx6
Published 06-07-2026Last modified 06-07-2026
Open JSON

Vulnerability summary

CVE-2026-55514 is a high (CVSS 7.1) Reachable Assertion vulnerability in vllm-project vllm. EPSS estimates a 0.66% chance of exploitation in the next 30 days, higher than 51.1% of scored vulnerabilities.

Overall risk
29/100
0100
Medium · default modelHow is this calculated?
CVSS score
7.1/10
010
High · v4.0 (CVE.org)
EPSS score
0.66%
0%100%
Low · 0.00 pp in 30 days
KEVNot listedIn no KEV catalog
RansomwareNone recordedNo known use recorded
Public exploits0No public exploits recorded

Advisory lineage

Upstream 0 · Downstream 0 · Related 1
CGA-GQ6P-W45V-M44W

Timeline

  1. 06-07-2026
    PublishedVulnerability first disclosed.
  2. 06-07-2026
    Last modifiedVulnerability information updated.

Description

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.

CVSS metrics

5 scores · 4 sources · 2 versions

EPSS trend

Probability

0.66%

Chance of exploitation in the next 30 days

Percentile

51%

Versus all other CVEs

30-day change

0.00 pp

From 0.66% on 21-09-2026

21-09-202621-10-2026
EPSS score
0.66%

Known exploited

Compare KEV catalogs

Not in any of the 3 tracked catalogs.

Public exploits

0 found

No public exploits indexed.

Weaknesses

CWE · root cause

Affected systems

Chainguard7 products
  • lmcache-cuda-12.8All versions (No fix recorded)
  • nemo-rl-cuda-13.0-vllmAll versions (No fix recorded)
  • py3.10-vllm-cuda-12.4All versions (No fix recorded)
  • py3.12-vllm-cuda-12.4All versions (No fix recorded)
  • tritonserver-backend-vllm-cuda-13.0< 25.11-r12
PyPI1 product
  • vllm≥ 0.12.0, < 0.24.0
Vllm1 product
  • vllm≥ 0.12.0, < 0.24.0
Vllm-project1 product
  • vllm≥ 0.12.0, < 0.24.0

4 vendors · 10 products

References

8 links