CVE-2026-54235
vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels
Description
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.
No summary for this CVE yet.
CVSS Vector Breakdown
Exploitability
AV:NAttack VectorNetwork
AC:LAttack ComplexityLow
PR:NPrivileges RequiredNone
UI:NUser InteractionNone
Scope
S:UScopeUnchanged
Impact
C:NConfidentialityNone
I:LIntegrityLow
A:LAvailabilityLow
Weaknesses
Affected Products
vllm
oss-projectaka aibrix
vllm-project
oss-projectaka vllm-project/vllm, vllm
Exploitability
Official Patch Available
References
Unlock Complete Vulnerability Intelligence
Get the full picture for CVE-2026-54235 and every CVE in our database. Create a free account — no credit card required.
Create Free AccountPlain-language analysis
Impact assessment and exploitation scenario in plain English
Attack graph visualization
Interactive attack path and kill chain mapping
Exploit details & PoC links
ExploitDB, Metasploit, GitHub PoCs with direct links
Nuclei scanner templates
Ready-to-use vulnerability scanner templates
Full remediation guide
Patch instructions, workarounds, and compliance impact
Interactive AI chat
Ask questions about this vulnerability in natural language
Related vulnerabilities
Semantically similar CVEs and attack patterns
REST API & MCP access
Integrate vulnerability data into your workflows