CVE-2026-54235
mediumpriority · track · 26EPSS 0.004 · 39 %ileDEEUUSEPSS · scored 2026-10-27
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.
cvss
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode⚠ sources disagree · low–medium · 2.7–6.9
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
affected products (6)
Products and version ranges known to be affected.
advisories (3)
Vendor and ecosystem advisories describing this.
- WID-SEC-W-2026-1897vllm: Mehrere SchwachstellenDeutsch2026-06-11csaf · cert_bundDE
Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um Sicherheitsmaßnahmen zu umgehen, einen Denial-of-Service-Zustand zu verursachen, Daten zu manipulieren oder vertrauliche Informationen offenzulegen.
- GHSA-7h4p-rffg-7823vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels2026-06-17ghsa · osvUS
## 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
- PYSEC-2026-3405vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels2026-07-13vendor · osvUS
## 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
also known as (6)
Other names and identifiers for this entity.
sources
Which sources assert this record, and when.
references (9)
External citations — patches, advisories, analysis.
- https://github.com/vllm-project/vllm/commit/d598d239737cfa37bcfcb98886ec3f3557fc7198cnnvd
- https://github.com/vllm-project/vllm/pull/45116cnnvd
- https://github.com/vllm-project/vllm/security/advisories/GHSA-7h4p-rffg-7823cnnvd
- https://github.com/vllm-project/vllm/commit/d598d239737cfa37bcfcb98886ec3f3557fc7198enisa_euvd
- https://github.com/vllm-project/vllm/pull/45116enisa_euvd
- https://github.com/vllm-project/vllm/security/advisories/GHSA-7h4p-rffg-7823enisa_euvd
- https://github.com/vllm-project/vllm/commit/d598d239737cfa37bcfcb98886ec3f3557fc7198Patchnvd
- https://github.com/vllm-project/vllm/pull/45116Issue Trackingnvd
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan