Disclosure summary
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).
Source-reported weakness categories
CWE-129
Source-specific records & product guidance
Sources retain their own attribution and scoring. Follow the original record to confirm affected versions, fixed releases, and configuration conditions.
NIST National Vulnerability Database · NVD-CVE-2026-100654
Open original source · Updated Oct 07, 2026
Only CPE matches marked vulnerable=true are indexed. AND/OR platform conditions must be checked in the original NVD record.
| Vendor | Product / association | Version / bounds |
|---|---|---|
| vllm | vllm | * {"versionEndExcluding":"0.29.0"} |
Original records & references
- NIST NVD record
- CVE Program record
- github.com — Mitigation, Vendor Advisory
- www.vulncheck.com — Third Party Advisory
PUBLISHED 2026-09-26T10:16:48-04:00
MODIFIED 2026-10-07T13:33:53-04:00
INGESTED 2026-10-10T20:45:41-04:00