Medium [CVE-2026-53923] Information disclosure via integer truncation
This medium-severity Red Hat Linux advisory covers CVE-2026-53923 affecting Red Hat AI Inference Server 3.3.
Android app · Google Play
Monitor future Red Hat Linux CVEs from your phone.
Choose a whole vendor or a precise platform, then receive matching security advisories by phone notification, email, or both. Coverage follows 32 official vendor sources and 160+ reviewed platform categories.
Summary
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.
A flaw was found in vLLM. Red Hat rates this issue as having Low impact for Red Hat AI products.
The upstream issue is limited information disclosure via integer truncation in vLLM sampling parameters. Red Hat OpenShift AI, Red Hat AI Inference Server, and Red Hat Enterprise Linux AI images are not considered affected because untrusted clients cannot control the vulnerable parameters in supported deployment models.
Red Hat severity: Low — CVSS 4.3 (CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N). Weakness: CWE-824.
Red Hat fixing advisory: RHSA-2026:59138, RHSA-2026:59139.
Affected product named by the advisory: Red Hat AI Inference Server 3.3.
Affected versions
No affected-version range was extracted from the source record. The vendor advisory is authoritative — check it before change work.
Official advisory · high-confidence parse· fetched 15 days ago·verify at source
- 0.23
- rhaiis/vllm-cuda-rhel9:1787161382
- rhaiis/vllm-rocm-rhel9:1787161803
- RHSA-2026:59138
- RHSA-2026:59139
Official advisory · high-confidence parse· fetched 15 days ago·verify at source
Mitigation checklist
- No mitigation is required for unaffected deployments. Restrict untrusted access to inference APIs as a general hardening measure.
Official advisory · high-confidence parse· fetched 15 days ago·verify at source
Discussion(0)
No comments yet. Share field notes, upgrade gotchas, or questions — verify against the vendor advisory before acting on community advice.
Sign in to join the discussion.