PatchTheCVECVE-2026-54235: vLLM is an inference and serving engine for large language models (LLMs)
CVE-2026-54235 is a medium-severity flaw (CVSS 6.5) affecting vllm. Below: why it ranks where it does, which versions are affected, what to do, and the exact commands.
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operators (<, >), which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagate to GPU sampling kernels, where they produce undefined behavior or CUDA errors that can crash the inference worker. This vulnerability is fixed
Why this priority
- Public exploit reference
- Remotely exploitable, no login, no user action
A fixed release or distro patch exists.
Risk facts
| CVSS score | 6.5 (Medium) |
| Attack vector | Network (remote) |
| Attack complexity | Low |
| Privileges needed | None |
| User interaction | None |
| EPSS exploit chance | 0.4% (top 61%) |
| CISA exploited list | No |
| Weakness | CWE-1287 |
| Published | 2026-06-22 |
| Last modified | 2026-10-25 |
Last updated 2026-10-25 · Sources: CVE Program, NVD, CISA KEV, EPSS and vendor advisories · How we score
Am I affected?
Timeline
- Published CVE record published
- Updated Record last modified
Scores and fixes here are computed automatically from those and other public sources. Confirm with the vendor advisory before changing production systems.
Quick answers
How do I fix CVE-2026-54235?
vllm: upgrade to 0.23.1. Exact commands for each OS are on this page.
Is CVE-2026-54235 being exploited?
CVE-2026-54235 is not on the CISA Known Exploited Vulnerabilities list at the time of the last update. Check again, as this can change.
What does CVE-2026-54235 affect?
CVE-2026-54235 affects vllm. Severity is medium (CVSS 6.5). vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operators (<, >), which silently evaluate to False for NaN and for positive Infinity in Python's IE
How urgent is CVE-2026-54235?
Priority 42/100. Public exploit reference; Remotely exploitable, no login, no user action
Software pages
Related CVEs
- CVE-2026-48746 CRITICAL 9.1 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-54232 HIGH 8.8 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-41523 HIGH 7.5 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-54236 MEDIUM 5.3 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-53923 HIGH 7.5 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)