CVE-2026-53923
vLLM is an inference and serving engine for large language models …
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.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4
- github.com/vllm-project/vllm/pull/44971
- github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e
- github.com/advisories/GHSA-5jv2-g5wq-cmr4
- nvd.nist.gov/vuln/detail/CVE-2026-53923
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-3403.yaml
- github.com/vllm-project/vllm
- pypi.org/project/vllm
- nvd.nist.gov/vuln/detail/CVE-2026-53923
- cve.org/CVERecord?id=CVE-2026-53923
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.