PYSEC-2026-3405 vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels

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 tha...

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

SummaryAll 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...

PT-2026-60017

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 tha...

The vulnerability of the start_power_clamp() function in the drivers/thermal/intel/intel_powerclamp.c file of the Linux kernel temperature control driver allows a hacker to cause a system failure.

The vulnerability of the startpowerclamp function in the drivers/thermal/intel/intelpowerclamp.c file of the Linux kernel temperature control driver is related to improper elimination of certain elements in the data sent to the client. Exploiting this vulnerability could allow an attacker to caus...

CVE-2026-54235

A flaw was found in vLLM, an inference and serving engine for large language models LLMs. The temperature validation gates, which use comparison operators, incorrectly handle Not-a-Number NaN and positive Infinity values in Python's IEEE 754 float semantics. These invalid values can bypass...

CVE-2026-47146 Color Control color-temperature assertion abort in EmberZNet v9.0.2

In EmberZNet v9.0.2 and earlier, malformed Color Control messages can lead to asserts that terminate the process. These messages must come from a device that has already joined the network. Only devices supporting the Color Control cluster may be impacted...

CVE-2026-54235

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 propagat...

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

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 propagat...

CVE-2026-54235

Summary: CVE-2026-54235 affects vLLM prior to 0.23.1rc0, where temperature validation gates using can silently mis-handle NaN and positive Infinity due to Python IEEE 754 behavior. This allows non-finite temperatures to bypass guards and propagate to GPU sampling kernels, causing undefined behav...

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

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 propagat...

CVE-2026-54235

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 propagat...

EUVD-2026-38402

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 propagat...

GHSA-7H4P-RFFG-7823 vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels

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 tha...

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

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 tha...

Improper Validation of Specified Type of Input

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Improper Validation of Specified Type of Input due to improper validation of the temperature parameter while sampling. An attacker can cause the...

PT-2026-50490

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.23.1rc0 Description Temperature validation gates use comparison operators that silently evaluate to False when encountering NaN Not a Number or positive Infinity due to Python's IEEE 754 float semantics. These values...

PT-2026-49095

Name of the Vulnerable Software and Affected Versions Glances versions prior to 4.5.5 Description The XML-RPC server implemented in glances/server.py and started with glances -s fails to validate the HTTP Host header. This allows a DNS rebinding attack, where an attacker can bypass the same-origi...

Astra Linux – Vulnerability in Linux 5.10

In the Linux kernel, the following vulnerability has been resolved: Wifi: mt76: mt7996 – fixed a potential memory leak when reading chip temperature. Without this fix, reading chip temperature would cause memory leaks...

Astra Linux – Vulnerability in Linux 5.10

In the Linux kernel, the following vulnerabilities have been resolved: Wifi: ath12k – Fixed issues with dfs-radar and temperature event locking. The ath12k active PDevs are protected by RCU, but the code responsible for handling DFS-radar and temperature events, which calls ath12kmacgetarbypdevid...

Astra Linux – Vulnerability in Linux 5.10

In the Linux kernel, the following vulnerability has been resolved: “ice”: fixed the devlink reload call trace. The commit 4da71a77fc3b “ice: read internal temperature sensor” introduced the use of the internal temperature sensor via HWMON. The functions icehwmoninit and icehwmonexit were added t...