vllm-project · vLLM · published 2026-06-22
CVE-2026-54235vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels
Routine No exploitation evidence; EPSS 0.4%.
CVE-2026-54235 is not known to be exploited in the wild. EPSS estimates a 0.4% chance of exploitation in the next 30 days, higher than 39% of all CVEs. This vLLM vulnerability: CVSS 6.9 (v4.0), attacks can be automated. Fixed upstream in vLLM 0.24.0. Routine: patch when convenient.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.24.0.
Patch events
AI toolingvLLM
vLLM security release: 0.24.0
Upgrade to
0.24.0Why: CVE-2026-54236: Public proof-of-concept exists (SSVC exploitation: poc).
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.4% (40th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 6.9 (v4.0)CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N | CNA / CISA ADP |
| SSVC exploitation | none | CISA Vulnrichment |
| SSVC automatable | Yes | CISA Vulnrichment |
| SSVC technical impact | partial | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vllm
< 0.23.1rc0(affected)
Description (from the CVE record)#
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 in 0.23.1rc0.
Quoted from the CVE Program record.