Vulnerability · CVE-2026-34756
vLLM is an inference and serving engine for large language models (LLMs).
Published Apr 6, 2026 · corrected/updated Aug 25, 2026 · vllm vllm · evidence confidence high
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.
Grounded briefings
Catalog interpretations for three audiences. Each brief cites ingested metadata and the original advisories below. They are not independent research and they do not invent exploit steps.
Executive
CVE-2026-34756 is a medium public vulnerability record for vllm vllm. It is not currently listed in the CISA Known Exploited catalog. Check the linked vendor or CERT advisories for patch status. This summary is a catalog interpretation of the ingested metadata and cites the original advisories below.
System administrator
Identify whether vllm vllm is in your estate, then compare installed versions with the affected ranges. Affected packages or ranges on record: vllm/vllm. Check the linked vendor or CERT advisories for patch status. Prefer the vendor or distribution advisory linked in Sources before changing production systems. This is a catalog interpretation, not a runbook.
Security analyst
Signals on file: CVSS 6.5, EPSS 0.8%. It is not currently listed in the CISA Known Exploited catalog. Weakness classes: CWE-1284, CWE-770. Sources contributing to this record: cve_org, epss, nvd. Public exploit references, when present, are outbound links only and are not proof of active exploitation. This is a catalog interpretation of stored metadata.
Exploitation and remediation
Exploitation evidence
Not listed as known exploited in CISA KEV. Not in CISA KEV or VulnCheck KEV.
Patch and remediation
No required-action text is stored yet. Use the vendor or CERT links in Sources for patch availability.
Safe detection guidance
Compare installed versions with the affected ranges below and verify the advisory from the original publisher. This site stores metadata and outbound links only; it does not ship exploit code or proof-of-concept payloads.
Code
The project this record applies to. Exploit listings stay in References.
Timeline
Detection, updates, and resolution for this record.
Apr 6, 2026 · NIST NVD
Detected
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
Aug 25, 2026 · NIST NVD
Updated
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
Affected
- cpe vllm/vllmversion unspecified
Sources
- CVE.orgVulnerability recordCVE-2026-34756
Official CVE identifier
cve.org - FIRST EPSSExploitation probabilityCVE-2026-34756
30-day exploitation probability 0.8%
first.org - NIST NVDVulnerability recordCVE-2026-34756
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 a
nvd.nist.gov