CVE-2026-53923
vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow
No known exploitation. EPSS puts it in the 39th percentile. A vendor fix is available.
What to do
The vendor has published a fix. Version details are below where the sources state them.
What it is
From the CVE record
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.
In plain language
No plain-language summary for this CVE yet.
Exploitation
Where each signal puts this CVE on the scale from published to confirmed exploited.
- CISA KEV
Not in the catalog. CISA has not confirmed exploitation.
- Public exploits
No public exploit or proof of concept found in the sources we track.
- EPSS
0.5% chance of exploitation activity in the next 30 days, which ranks it in the 39th percentile of scored CVEs.
Exploit Prediction Scoring System, FIRST.org. A probability, not a confirmation.
Lifecycle
5 events over 2 days, from the signal feeds we watch.
- Patch availablerecord updated
- Publishedweakness classified, att&ck mapped
Affected products
Technical detail
CVSS 3.1 vector
Open in the CVSS calculatorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Scored 7.5 by NVD.
How it is reached
- Attack Vector NetworkExploitable remotely over the network without any special conditions
- Attack Complexity LowNo special conditions — the attack can be reliably reproduced
- Privileges Required NoneNo authentication required — anyone can exploit this
- User Interaction NoneNo user interaction needed — fully automated exploitation
Scope
- Scope UnchangedImpact is limited to the vulnerable component itself
Impact if exploited
- Confidentiality HighTotal information disclosure — all data in the component is compromised
- Integrity NoneNo integrity impact
- Availability NoneNo availability impact
Weaknesses
ATT&CK techniques
Mapped from the weaknesses above (CWE to ATT&CK), not observed in attacks.
Sources
Watch the software you run.
My Stack ranks new CVEs for your products by real-world exploitation, so the next serious one reaches you without reading every advisory.
We'll flag the next CVE, public exploit or patch for Vllm, not every advisory.
A free account adds
- The full version matrix and every affected product
- Exploit links, proofs of concept and Metasploit modules
- Email alerts for the products you watch
- The same data over REST API, MCP and CLI