CVE-2026-100652

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 4.0

8.2CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

CVSS 3.1

7.5CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

EPSS

0.4% chance of exploitation in the next 30 days; higher than 35% of CVEs (scores of 2026-10-25)

CWE

CWE-20

Published

2026-09-26

Modified

2026-10-06

Record from

the NVD, synced 2026-10-19

Affected

• vllm:vllm

Packages (OSV)

References

• https://github.com/vllm-project/vllm/security/advisories/GHSA-qff2-492f-9fm4
• https://www.vulncheck.com/advisories/vllm-0.22.0-through-0.23.0-denial-of-service-via-stop-token-ids

Check your stackJSON