CVE-2026-53923
Last modified
CVE-2026-53923 is a high-severity vulnerability rated 7.5/10 on the CVSS scale. 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. EPSS estimates a 0.28% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.5.5, < 0.23.1 |
References
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2026-53923?
How severe is CVE-2026-53923?
How do I fix CVE-2026-53923?
How Strix Helps
- How Strix found a critical auth bypass in etcdStrix autonomously discovered a critical authentication bypass in etcd, later designated CVE-2026-33413.
- Autonomous PentestingAI agents that find and validate exploitable vulnerabilities like this one across your applications.
- PR ReviewsPentest every pull request so vulnerable code is caught before it ships to production.
- AI Penetration TestingHow AI-driven penetration testing continuously covers your attack surface.
Related CVEs from 2026
- CVE-2026-53913Improper Authentication, Missing Authentication for Critical…9.8
- CVE-2026-53914In JetBrains Kotlin before 2.4.20 code execution was possibl…9.8
- CVE-2026-53915In JetBrains GoLand before 2026.1.3 remote code execution wa…8.8
- CVE-2026-53916Memory Allocation with Excessive Size Value vulnerability in…7.5
- CVE-2026-53917Memory Allocation with Excessive Size Value vulnerability in…7.5
- CVE-2026-5392Heap out-of-bounds read in PKCS7 parsing. A crafted PKCS7 me…5.4
- CVE-2026-53925Glances is an open-source system cross-platform monitoring t…7.8
- CVE-2026-53926NocoDB is software for building databases as spreadsheets. P…6.3
- CVE-2026-53927NocoDB is software for building databases as spreadsheets. P…5.1
- CVE-2026-53928NocoDB is software for building databases as spreadsheets. P…6.3
- CVE-2026-53929NocoDB is software for building databases as spreadsheets. P…5.1
- CVE-2026-5393Dual-Algorithm CertificateVerify out-of-bounds read. When pr…9.1
Are you affected by CVE-2026-53923?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
