Vulnerability · Published Jun 22, 2026 · Assigned by GitHub_M
CVE-2026-53923vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow
Medium 5.3
In plain English
A medium-severity information exposure in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 42% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official 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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | vllm | 0.24.0 | GHSA-5jv2-g5wq-cmr4 |
| PyPI | vllm | no fix listed | PYSEC-2026-3403 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | >= 0.5.5, < 0.23.1rc0 |
Weakness: CWE-681, CWE-200 · 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
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4 x_refsource_CONFIRM
- https://github.com/vllm-project/vllm/pull/44971 x_refsource_MISC
- https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e x_refsource_MISC