Signal is active with 1 mentions in latest observed window
Recommended action window: Monitor and triage in normal cycle
NVD 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.
Priority
LOW
Exploitation
NONE
PoC
NONE
Patch
AVAILABLE
Momentum
NONE
If you run products in this scope, you should treat this CVE as relevant to your environment.
CVE-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-com… https://www.cve.org/CVERecord?id=CVE-2026-34756
Post summary
The post discloses a denial‑of‑service vulnerability in vLLM affecting versions 0.1.0 through 0.18.x, with no evidence of PoC, exploit code, active exploitation, or patched remedy.
1 of 1 entries
| Part | Vendor | Product | Version | Target SW | Target HW |
|---|---|---|---|---|---|
| App | vllm | vllm | - | - | - |