What’s Vulnerable › Vulnerabilities

CVE-2026-53923: vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow

• Severity: high (CVSS 7.5 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.5% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-06-22 · updated 2026-10-25
• Weakness: CWE-200

Description

vLLM is an inference and serving engine for large language models (LLMs). From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels (csrc/quantization/gguf/gguf_kernel.cu) causes partial tensor processing. The output tensor is allocated at full size via torch::empty (uninitialized memory), but the dequantize CUDA kernel processes only a truncated number of elements. The unfilled portion of the output tensor retains whatever was previously in GPU memory. In multi-tenant inference deployments, this residual GPU memory may contain tensor data from other users' inference requests, constituting information disclosure. This vulnerability is fixed in 0.23.1rc0.

Affected products

• vllm-project vllm: from 0.5.5 before 0.23.1 — fixed in 0.23.1

How to fix

Upgrade to a fixed version: vllm-project vllm 0.23.1. Check the vendor advisory for mitigations.

References

• https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e
• https://github.com/vllm-project/vllm/pull/44971
• https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4

Get alerted when CVE-2026-53923 or the next vulnerability affects your stack