CVE-2026-34756

MEDIUM EPSS 21.0%
Published Apr 6, 20262mo ago · Modified Jun 17, 20262w ago
6.5 CVSS 3.1
Medium
Find Similar
Published Apr 6, 2026 2mo ago
Last Modified Jun 17, 2026 2w ago

Description

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.

CVSS Details

Base Score
6.5
Exploitability
2.8
Impact
3.6
Vector string
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Attack Vector Network
Attack Complexity Low
Privileges Required Low
User Interaction None
Scope Unchanged
Confidentiality None
Integrity None
Availability High

Threat Intelligence

EPSS Exploit Probability
21.0% percentile
Exploit & Patch Status
No Known Exploit
Patch Available

Weaknesses 1

CWE-770

Affected Products 1

VendorProductVersionRange
vllmvllm*≥0.1.0  –  <0.19.0

References 3

  • github.com https://github.com/vllm-project/vllm/commit/b111f8a61f100fdca08706f41f29ef3548de7380
    Patch
  • github.com https://github.com/vllm-project/vllm/pull/37952
    Issue TrackingPatch
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-3mwp-wvh9-7528
    PatchVendor Advisory

Remediation

  • github.com https://github.com/vllm-project/vllm/commit/b111f8a61f100fdca08706f41f29ef3548de7380
    Patch
  • github.com https://github.com/vllm-project/vllm/pull/37952
    Issue TrackingPatch
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-3mwp-wvh9-7528
    PatchVendor Advisory