vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow (vllm-project vllm)
At a glance
- Source
- NVD
- EPSS
- EPSS 0.48 % · percentile 42 ()
- State
- PUBLISHED
- Published
- Updated
- Assigner
- GitHub_M
- NVD status
- Analyzed
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.
Weaknesses (CWE)
- CWE-681 — Incorrect Conversion between Numeric Types
- CWE-200 — Exposure of Sensitive Information to an Unauthorized Actor
References
Scores
| Version | Score | Vector | Scored by |
|---|---|---|---|
| CVSS 4.0 | MEDIUM 5.3 | 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 | GitHub_M |
| CVSS 4.0 | MEDIUM 5.3 | 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 | NVD · security-advisories@github.com (Secondary) |
| CVSS 3.1 | HIGH 7.5 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N | NVD · nvd@nist.gov (Primary) |
Advisories
- GHSA-5jv2-g5wq-cmr4 — vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving
- PYSEC-2026-3403 — vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving
European references
- ENISA EUVD · EUVD-2026-38400
- GCVE · GCVE-0-2026-53923
Affected configurations (NVD CPE)
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*≥ 0.5.5 < 0.23.1
Affected products
| Product | Versions |
|---|---|
| vllm-project · vllm | affected >= 0.5.5, < 0.23.1rc0 |
Sources
| Source | Licence |
|---|---|
| CVE List (CVEProject cvelistV5) | CVE Program Terms of Use |
| EPSS (FIRST.org) | FIRST — attribution requested |
| ENISA EUVD | ENISA — reproduction authorised, source acknowledged |
| NVD (NIST) via fkie-cad/nvd-json-data-feeds | Public domain — this product uses data from the NVD API but is not endorsed or certified by the NVD |