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 2

References 3

• github.com https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e
• github.com https://github.com/vllm-project/vllm/pull/44971
• github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4

Remediation