SOURCE-LINKED INTELLIGENCE

GHSA-5jv2-g5wq-cmr4: vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving

OSV AI package advisories · observation · Jun 17, 2026 · UTC

## Summary 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. ## Root Cause The `to_

Read original source ↗ Open in workspace

recordType

vulnerability

status

active

evidenceStatus

reported

region

Global