Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

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

Quick assessment

Affected
vllm-project vllm
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

vLLM是vLLM团队开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.23.1rc0之前版本存在软件供应链问题漏洞，该漏洞源于温度验证门使用比较运算符（<, >），导致NaN和正无穷值绕过检查并传播到GPU采样内核，产生未定义行为或CUDA错误，可能导致推理工作进程崩溃。

AI Predicted 5.3 Difficulty: Easy EPSS 0.45% · P37

Possible ATT&CK Techniques 1 AI

T1068 · Exploitation for Privilege Escalation

Affected Version Matrix 1

VendorProduct Version RangeStatus
vllm-project vllm < 0.23.1rc0 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-54235

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N
Source: CVE Program / CVE List V5
Vulnerability Type
CWE-1287
Source: CVE Program / CVE List V5
Vulnerability Title
vLLM 软件供应链问题漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
vLLM是vLLM团队开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.23.1rc0之前版本存在软件供应链问题漏洞，该漏洞源于温度验证门使用比较运算符（<, >），导致NaN和正无穷值绕过检查并传播到GPU采样内核，产生未定义行为或CUDA错误，可能导致推理工作进程崩溃。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
vllm-project vllm < 0.23.1rc0 -

II. Public POCs for CVE-2026-54235

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-54235

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-54235 (2)

Vendor Advisories for CVE-2026-54235 (1)

Same Patch Batch · vllm-project · 2026-06-22 · 8 CVEs total

CVE-2026-48746 9.1 CRITICAL vLLM: OpenAI auth bypass
CVE-2026-54232 8.8 HIGH vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile
CVE-2026-41523 7.5 HIGH vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arb
CVE-2026-47155 6.5 MEDIUM vLLM: Artifact Pin Decay in vLLM allows pinned deployments to load unpinned code, weights,
CVE-2026-54233 6.5 MEDIUM vLLM: OOM Denial of Service via Audio Decompression Bomb
CVE-2026-54236 5.3 MEDIUM vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router
CVE-2026-53923 vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overfl

IV. Related Vulnerabilities

Same product: vllm
Same vendor: vllm-project
Same weakness: CWE-1287

V. Comments for CVE-2026-54235

No comments yet

Leave a comment