Servers and applications
CVE-2026-54235
temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels
- Severity
- Medium 6.9
- Published
- 11 Jun 2026
- Last changed
- 25 Oct 2026
- Added to UpHeron
- 3 Nov 2026
- Fixed in
- 0.23.1, 0.24.0
- Exploit chance
- 0.4% in the next 30 daysHigher than 39% of CVEs. EPSS by FIRST, 19 Nov 2026
- Weakness
- CWE-1287
- Attack
- Over the network · No login needed · No user action needed
- Attacker can
- Slow it down
- CVSS vector
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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X- Also known as
- GHSA-7h4p-rffg-7823
- Sources
- NVD, Project advisories (GitHub)
Description
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.
sampling_params.py:384:
sampling_params.py:462:
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.
Crash of inference worker on GPU kernel execution with NaN/Inf softmax input, degrading service for all concurrent users.
Affected software
| Software | Affected versions |
|---|---|
vLLMServers and applications · cpe:a:vllm:vllm |
|
vLLMServers and applications · github:vllm-project/vllm |
|
About vLLM
open-source software for large language model inference
- Docker Hub pulls
- 44,195,225Docker Hub, 15 Nov 2026
- GitHub stars
- 96,943GitHub, 15 Nov 2026
- Forks
- 24,836GitHub, 15 Nov 2026
- Latest release
- v0.33.0rc3GitHub, 15 Nov 2026
- Released
- 2 Nov 2026GitHub
- License
- Apache Software License 2.0Wikidata
- First published on GitHub
- 9 Feb 2023GitHub
Website Source code Docker image
Vulnerabilities in vLLM
- In our list
- 169
- Published in the last 12 months
- 150
- Critical, last 12 months
- 6
- High, last 12 months
- 63
- Known exploited
- 0
- CVE-2026-130686vLLM 0.6.0 before 0.33.0 Resource Exhaustion via Multi-Image RequestsHigh 8.7 18 Nov 2026
- CVE-2026-130684vLLM before 0.33.0 Path Traversal via speculators_config verifier.name_or_pathMedium 5.3 18 Nov 2026
- CVE-2026-130685vLLM 0.28.0 before 0.33.0 Unauthenticated DoS via Out-of-Range Prompt Token IDHigh 8.7 18 Nov 2026
- GHSA-xgh8-qwjh-q853/v1/systemone bypasses the --trust-request-chat-template gateMedium 6.5 18 Nov 2026
- CVE-2026-129356vllm-project vllm Common Prefix single_type_kv_cache_manager.py race conditionLow 2.3 15 Nov 2026
- CVE-2026-126394vLLM 0.30.0 before 0.31.0 Resource Exhaustion via OpenPangu Video Backend num_framesMedium 6.9 13 Nov 2026
References
- NVD https://nvd.nist.gov/vuln/detail/CVE-2026-54235
- CVE.org https://www.cve.org/CVERecord?id=CVE-2026-54235
- GitHub Advisory Database https://github.com/advisories/GHSA-7h4p-rffg-7823
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-7h4p-rffg-7823