{"id":"CVE-2026-53923","aliases":["GHSA-5jv2-g5wq-cmr4","PYSEC-2026-3403"],"url":"https://o3.security/vulnerability/CVE-2026-53923","summary":"vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow","details":"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.","published":"2026-06-22T21:55:42.001Z","modified":"2026-08-07T21:41:18.075122Z","cvss":null,"epss":null,"cisaKev":null,"exploitsKnown":0,"affectedPackages":[{"ecosystem":"PyPI","name":"vllm","fixedVersion":"0.24.0"}],"fix":{"url":"https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e","label":"vllm-project/vllm@f219788"},"references":[{"type":"ADVISORY","url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/53xxx/CVE-2026-53923.json"},{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-53923"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/pull/44971"}],"provenance":{"sources":["OSV.dev","FIRST.org (EPSS)"],"lastVerified":"2026-08-07T21:41:18.075122Z"}}