CVE-2026-53923

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.

CVSS 4.0

5.3CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N

CVSS 3.1

7.5CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

EPSS

0.5% chance of exploitation in the next 30 days; higher than 41% of CVEs (scores of 2026-10-25)

CWEs

CWE-200, CWE-681

Published

2026-06-22

Modified

2026-10-25

Record from

the NVD, synced 2026-10-25

Affected

• vllm:vllm

Packages (OSV)

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

Check your stackJSON