Off-by-one in vLLM - CVE-2026-115916
Published: October 21, 2026 / Updated: November 2, 2026
Vulnerability identifier: #VU156676
CSH Severity: Low
CVSS v4: 7.1 [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]
CVE-ID: CVE-2026-115916
CWE-ID: CWE-193
Exploitation vector: Remote access
Exploit availability:
No public exploit available
Vulnerability details
The vulnerability allows a remote user to cause a denial of service by crashing the vLLM engine.
The vulnerability exists due to an off-by-one error in vLLM's input token ID validation when processing pre-tokenized prompts. A remote user can submit a prompt containing a token ID equal to the model's vocabulary size to trigger an out-of-range embedding lookup at tensor-parallel size 1, causing a CUDA device-side assertion that invalidates the engine's CUDA context and stops the engine.
The crash affects models whose vocabulary size is a multiple of 64 and whose tokenizer.vocab_size is one greater than the largest real token ID.
Affected software
vLLM
How to mitigate CVE-2026-115916
Install security update from vendor's website.
vLLM - update to 0.32.0