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.
Metrics
Affected Vendors & Products
| Vendors | Products |
|---|---|
| Vllm-project |
|
No data.
No data.
References
History
Tue, 23 Jun 2026 01:30:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Vllm-project
Vllm-project vllm |
|
| Vendors & Products |
Vllm-project
Vllm-project vllm |
Mon, 22 Jun 2026 22:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels | |
| Weaknesses | CWE-1287 | |
| References |
| |
| Metrics |
cvssV4_0
|
MITRE
Status: PUBLISHED
Assigner: GitHub_M
Published: 2026-06-22T21:59:02.710Z
Updated: 2026-06-22T21:59:02.710Z
Reserved: 2026-06-12T16:25:43.084Z
Link: CVE-2026-54235
Vulnrichment
No data.
NVD
No data.
Redhat
No data.