CVE-2026-34756 | vLLM Affected by Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server

vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionRequest Pydantic models, an unauthenticated attacker can send a single HTTP request with an astronomically large n value. This completely blocks the Python asyncio event loop and causes immediate Out-Of-Memory crashes by allocating millions of request object copies in the heap before the request even reaches the scheduling queue. This vulnerability is fixed in 0.19.0.

Published: 2026-04-06 Last update: 2026-04-20 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2026-34756 is rated Low Risk (28.8/100): CVSS Medium severity, with low exploitation likelihood (EPSS 0.03%). Monitor for updates and reassess as exploit intelligence or EPSS changes.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Exploit prediction scoring system (EPSS) score for CVE-2026-34756

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-04-07 — 0.03% —

Full EPSS history (1 record total)

Common vulnerability scoring system (CVSS) metrics for CVE-2026-34756

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
6.5 3.1 MEDIUM
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:L)
A normal user session is enough; they don’t have to be admin.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:N)
Doesn’t really leak secrets in a meaningful way.
Integrity (I:N)
Data isn’t meaningfully altered or forged.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 2.8 3.6 [email protected]

Weakness enumeration for CVE-2026-34756

GitHub Security Advisory for CVE-2026-34756

GHSA-3mwp-wvh9-7528 · Severity: medium · Ecosystem: pip — vLLM: Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server

OS Trackers for CVE-2026-34756

vendor priority summary link
redhat high — https://access.redhat.com/security/cve/CVE-2026-34756

Affected software / configurations for CVE-2026-34756

Vendor Product Version Raw CPE
vllm vllm >= 0.1.0, < 0.19.0 cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

References for CVE-2026-34756

cvelogic Threat Intelligence