vLLM before 0.29.0 accepts user-controlled stop_token_ids on the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoints but validates only that the values are integers, not that each token id is within the model vocabulary/logits range. When min_tokens > 0, the stop token ids are used as logits indices to suppress stop tokens, so an out-of-range id reaches a CUDA indexing operation (index_put_) and triggers a device-side assertion. An authenticated API user can send a single malformed completion request that returns 500 Internal Server Error and puts EngineCore into a fatal state, causing subsequent requests to fail until the service is restarted (denial of service).
References
| Link | Resource |
|---|---|
| https://github.com/vllm-project/vllm/security/advisories/GHSA-v5gm-qgmv-gc6c | Mitigation Vendor Advisory |
| https://www.vulncheck.com/advisories/vllm-before-0.29.0-denial-of-service-via-out-of-range-stop-token-ids | Third Party Advisory |
Configurations
History
07 Oct 2026, 17:33
| Type | Values Removed | Values Added |
|---|---|---|
| CPE | cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* | |
| First Time |
Vllm vllm
Vllm |
|
| References | () https://github.com/vllm-project/vllm/security/advisories/GHSA-v5gm-qgmv-gc6c - Mitigation, Vendor Advisory | |
| References | () https://www.vulncheck.com/advisories/vllm-before-0.29.0-denial-of-service-via-out-of-range-stop-token-ids - Third Party Advisory |
26 Sep 2026, 14:16
| Type | Values Removed | Values Added |
|---|---|---|
| New CVE |
Information
Published : 2026-09-26 14:16
Updated : 2026-10-07 17:33
NVD link : CVE-2026-100654
Mitre link : CVE-2026-100654
CVE.ORG link : CVE-2026-100654
JSON object : View
Products Affected
vllm
- vllm
CWE
CWE-129
Improper Validation of Array Index