All vulnerabilities

Servers and applications

CVE-2026-93436

vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments. Remote attackers can submit requests with max_tokens=0 to exhaust decode-worker memory without bound until the worker restarts.

Severity
High 8.7
Published
17 Sept 2026
Last changed
28 Sept 2026
Added to UpHeron
3 Nov 2026
Exploit chance
0.8% in the next 30 daysHigher than 55% of CVEs. EPSS by FIRST, 19 Nov 2026
Weakness
Memory leak (CWE-401)
Attack
Over the network · No login needed · No user action needed
Attacker can
Take it down
CVSS vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/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
Sources
NVD

Affected software

SoftwareAffected versions
vLLMServers and applications · cpe:a:vllm:vllm
  • Every version up to 0.29.0

About vLLM

open-source software for large language model inference

From Wikidata, CC0 1.0.
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

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-93436
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-93436