CVE-2026-100652 PUBLISHED

vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids

Assigner: VulnCheck
Reserved: 26.09.2026 Published: 26.09.2026 Updated: 26.09.2026

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: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 Score: 8.2

Exploitability Metrics		Vulnerable System Impact Metrics		Subsequent System Impact Metrics
Attack Vector	Network	Confidentiality	None	Confidentiality	None
Attack Complexity	High	Integrity	None	Integrity	None
Attack Requirements	Present	Availability	High	Availability	None
Privileges Required	None
User Interaction	None

CVSS 4.0

CVSS Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H
CVSS Score: 5.9

Attack Vector	Network	Scope	Unchanged
Attack Complexity	High	Confidentiality Impact	None
Privileges Required	None	Integrity Impact	None
User Interaction	None	Availability Impact	High

CVSS 3.1

Product Status

Vendor	vllm-project
Product	vllm
Versions	Default: unaffected affected from 0.22.0 to 0.24.0 (excl.) Version 0.24.0 is unaffected

CVE-2026-100652 PUBLISHED

vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids

Metrics

Product Status

Credits

References

Problem Types