CVEvulnerability

CVE-2026-100654

7.1 HIGH Published 2026-09-26 Modified 2026-10-07 Official page ↗
Status
Analyzed
Published
2026-09-26
Last modified
2026-10-07
Assigner
[email protected]
CVSS 4.0 ([email protected])
7.1 HIGH — CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
CVSS 3.1 ([email protected])
6.5 MEDIUM — CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Weaknesses
CWE-129

Description

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).

Affected configurations

• vllm vllm (< 0.29.0)

Related

Weakness · CWE (1)

  • CWE-129 Improper Validation of Array Index weakness

References