vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels
CVE-2026-54235 · GHSA-7h4p-rffg-7823 · published 2026-06-17 · updated 2026-07-17
- Severity
- Medium
- CVSS score
- 6.5
- Chance of exploitation (EPSS)
- 0.45%
- Fixed in
- 0.24.0
- Exploitation No known exploitation
- Automatable Yes
- Technical impact Partial
- CISA SSVC
Crash of inference worker on GPU kernel execution with NaN/Inf softmax input, degrading service for all concurrent users.
Upgrade vllm to 0.24.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
Add math.isfinite(self.temperature) check in verifyargs(). Reject non-finite float values with a 400 error.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| vllm | PyPI | >= 0.8.5, <= 0.23.0 | 0.24.0 |
- CriticalLiteLLM has SQL Injection in Proxy API key verificationlitellmExploited
- Criticaln8n Vulnerable to Remote Code Execution via Expression Injectionn8n, n8nExploited
- HighLiteLLM has a sandbox escape in custom-code guardraillitellmExploited
- HighLangflow affected by Remote Code Execution via validate_code() exec()langflowExploited
- CriticalJupyter MCP Server: Browser DNS rebinding can hijack the Jupyter backend through management routesjupyter-mcp-server
- Criticalmem0ai Databricks vector store vulnerable to SQL injectionmem0ai
- CriticalvLLM: OpenAI auth bypassvllm
- CriticalvLLM has RCE In Video Processingvllm
- CriticalvLLM Allows Remote Code Execution via PyNcclPipe Communication Servicevllm
- CriticalvLLM Vulnerable to Remote Code Execution via Mooncake Integrationvllm
- CriticalCVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0vllm
- CriticalvLLM Deserialization of Untrusted Data vulnerabilityvllm
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.