Incorrect Conversion between Numeric Types in vLLM - CVE-2026-53923
Published: July 28, 2026
Vulnerability identifier: #VU139878
CSH Severity: Medium
CVSS v4: 4.6 [CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N]
CVE-ID: CVE-2026-53923
CWE-ID: CWE-681
Exploitation vector: Remote access
Exploit availability:
No public exploit available
Vulnerability details
The vulnerability allows a remote attacker to disclose sensitive information.
The vulnerability exists due to incorrect conversion between numeric types in GGUF dequantize kernels in csrc/quantization/gguf/gguf_kernel.cu when processing a crafted GGUF model with tensor dimensions whose product exceeds INT_MAX. A remote attacker can supply a specially crafted GGUF model file to disclose sensitive information.
User interaction is required to load the crafted model for inference serving, and the issue can expose residual GPU memory from prior requests in multi-tenant deployments.
Affected software
vLLM
How to mitigate CVE-2026-53923
Install security update from vendor's website.
vLLM - update to 0.24.0