CVE-2026-54235 — vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels

2026-10-03T03:32:24.425725+00:00

Affected: vllm-project vllm

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.

GHSA-7h4p-rffg-7823 — vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels

2026-10-03T03:32:24.425785+00:00

Affected: PyPI: vllm

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

`sampling_params.py:462`: ```python 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

Most recent entries from all

CVE-2026-54235 — vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels

GHSA-7h4p-rffg-7823 — vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels