High severity · published Sep 26, 2026
CVE-2026-100652
vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids
7.5
CVSS
0.4%
EPSS
No
On KEV
Description
vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
None
Integrity
None
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.4% · higher than 36% 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, NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-100652
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-100652
vendor-advisory
https://github.com/vllm-project/vllm/security/advisories/GHSA-qff2-492f-9fm4
third-party-advisory
https://www.vulncheck.com/advisories/vllm-0.22.0-through-0.23.0-denial-of-service-via-stop-token-ids
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