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.
References
| Link | Resource |
|---|---|
| https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e | Patch |
| https://github.com/vllm-project/vllm/pull/44971 | Issue Tracking |
| https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4 | Third Party Advisory |
Configurations
History
No history.
Information
Published : 2026-06-22 23:16
Updated : 2026-06-24 16:51
NVD link : CVE-2026-53923
Mitre link : CVE-2026-53923
CVE.ORG link : CVE-2026-53923
JSON object : View
Products Affected
vllm
- vllm