All vulnerabilities

Servers and applications

CVE-2026-53923

GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving

Severity
Medium 5.3
Published
11 Jun 2026
Last changed
25 Oct 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.23.1, 0.24.0
Exploit chance
0.5% in the next 30 daysHigher than 42% of CVEs. EPSS by FIRST, 19 Nov 2026
Weakness
Information exposure (CWE-200)Incorrect numeric conversion (CWE-681)
Attack
Over the network · No login needed · Needs someone to view a page or file
Attacker can
Read some data · Change some data
CVSS 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/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
Also known as
GHSA-5jv2-g5wq-cmr4
Sources
NVD, Project advisories (GitHub)

Description

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.

The to_cuda_ggml_t function pointer type at ggml-common.h:1067 declares its element count parameter as int (32-bit):

All dequantize kernel functions (dequantize_block_cuda, dequantize_row_q2_K_cuda, etc. in dequantize.cuh) inherit this int k parameter and use it as the kernel launch grid size:

In ggml_dequantize() at gguf_kernel.cu:85, the caller passes m * n (an int64_t product) to this int k parameter:

From vllm-project/vllm's security advisory. Shortened; the full text is there.

Affected software

SoftwareAffected versions
vLLMServers and applications · cpe:a:vllm:vllm
  • From 0.5.5 before 0.23.1
vLLMServers and applications · github:vllm-project/vllm
  • From 0.5.5 before 0.24.0

About vLLM

open-source software for large language model inference

From Wikidata, CC0 1.0.
Docker Hub pulls
44,195,225Docker Hub, 15 Nov 2026
GitHub stars
96,943GitHub, 15 Nov 2026
Forks
24,836GitHub, 15 Nov 2026
Latest release
v0.33.0rc3GitHub, 15 Nov 2026
Released
2 Nov 2026GitHub
License
Apache Software License 2.0Wikidata
First published on GitHub
9 Feb 2023GitHub

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-53923
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-53923
  • GitHub Advisory Database https://github.com/advisories/GHSA-5jv2-g5wq-cmr4
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4