{"cve":"CVE-2026-53923","nvd":{"published":"2026-06-22T23:16:30.737","modified":"2026-10-25T23:10:00.167","status":"Analyzed","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.","cvss_v4":{"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N","score":5.3},"cvss_v3":{"version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N","score":7.5},"cwes":["CWE-200","CWE-681"],"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"],"products":["vllm:vllm"],"source":"nvd","synced_at":"2026-10-25T23:44:33.281319194+00:00"},"epss":{"cve":"CVE-2026-53923","score":0.00484,"percentile":0.4143,"date":"2026-10-25"},"kev":null,"osv":[{"id":"GHSA-5jv2-g5wq-cmr4","url":"https://osv.dev/vulnerability/GHSA-5jv2-g5wq-cmr4","summary":"vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving","modified":"2026-09-10T03:51:07.886370970Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":[">=0.5.5 <0.24.0"],"fixed":["0.24.0"]}]},{"id":"PYSEC-2026-3403","url":"https://osv.dev/vulnerability/PYSEC-2026-3403","summary":"vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving","modified":"2026-07-13T16:33:32.223822993Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":[">=0.5.5 <=0.23.0"],"fixed":[]}]}],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}