Advisory

PYSEC-2026-3405

Also known as: CVE-2026-54235, GHSA-7h4p-rffg-7823

Summary

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

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

Severity

Not rated by the source.

Dates

Published
2026-07-13 15:46 UTC
Modified
2026-07-13 16:33 UTC

Affected packages and fixes

vllm

PyPI · All systems

Affected

  • introduced 0, last affected 0.23.0 (ecosystem)

Fixed versions

None listed

Fix

No fixed version is listed.

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: PyPA Advisory Database · CC BY 4.0

Sources & licences