Medium severity · published Oct 25, 2026
CVE-2026-116173
vLLM 0.22.0 before 0.24.0 Denial of Service via gRPC output_candidates.token_ids
New
5.9
CVSS
0.3%
EPSS
No
On KEV
Description
vLLM from 0.22.0 before 0.24.0 contains a denial of service vulnerability that allows remote attackers to terminate EngineCore by bypassing logprob_token_ids limits in the Rust gRPC frontend. Attackers can send Generate or GenerateStream requests with output_logprobs enabled and more than 128 output_candidates.token_ids, triggering a fatal sampler exception that crashes the engine.
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H
Attack vector
Network
Complexity
High
Privileges
None
User interaction
None
Confidentiality
None
Integrity
None
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.3% · higher than 28% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
VL
vllm · vllm-project
0.22.0 before 0.24.0 · source: vendor
Affected product
VL
vllm
vllm-project
More from vllm
9.8
CVE-2026-25960
SSRF Protection Bypass in vLLM
9.8
CVE-2024-9053
vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer() RPC server entrypoints
9.1
CVE-2026-48746
vLLM: OpenAI auth bypass
8.8
CVE-2026-54232
vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile
8.8
CVE-2026-27893
vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out