INCIDENT MAP

Browse / Unbounded Consumption / CVE-2026-54235

vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels

CVE-2026-54235 · 2026-06-17 moderate

Class
Unbounded Consumption (filed by a model that read the advisory)
Technique
Denial of service
Affected
vllm (PyPI)
Gets past
Input filter or sanitiser
CVSS
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L
EPSS
0.4% chance of exploitation in 30 days

How it works, in short

Temperature checks use comparisons that let NaN and positive infinity through, so these values reach GPU sampling kernels and crash the inference worker. (Our summary, written by a model. The source text is below.)

Details

Summary

All 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. Note: -Infinity is correctly caught.

Root Cause

sampling_params.py:384:

if 0 < self.temperature < _MAX_TEMP:  # NaN → False; +Inf → False

sampling_params.py:462:

if self.temperature < 0.0:            # NaN → False; +Inf → False
    raise VLLMValidationError(...)

No math.isnan() or math.isinf() check exists anywhere in sampling_params.py.

Python semantics (verified): float('nan') < 0.0 → False, float('inf') < 0.0 → False.

Impact

Crash of inference worker on GPU kernel execution with NaN/Inf softmax input, degrading service for all concurrent users.

Remediation

Add math.isfinite(self.temperature) check in _verify_args(). Reject non-finite float values with a 400 error.

Fix

A fix for this vulnerability was merged here: https://github.com/vllm-project/vllm/pull/45116

References

Source: GitHub Advisory Database, used under CC BY 4.0.