EUVD-2026-97575

ExLlamaV3’s EXL3 loader uses an untrusted, model-supplied index to select a CUDA kernel without first verifying that the index is within bounds. A malicious model can force the code to read and invoke an out‑of‑range function pointer, resulting in a reproducible crash. Under specific conditions...

CVE-2026-73558

vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x 2 d in activationkernels.cu can cause actandmulkernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or...

CVE-2026-73558 vLLM: Cross-User Data Leak Vulnerability

vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x 2 d in activationkernels.cu can cause actandmulkernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or...

CVE-2026-73558

vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x 2 d in activationkernels.cu can cause actandmulkernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or...

CVE-2026-73558 vLLM: Cross-User Data Leak Vulnerability

vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x 2 d in activationkernels.cu can cause actandmulkernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or...

PT-2026-71673

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.27.0 Description An integer overflow occurs in the calculation blockIdx.x 2 d within the activation kernels.cu file. This flaw can cause the act and mul kernel function to consume input from another user within the sam...

vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving

Summary Integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels csrc/quantization/gguf/ggufkernel.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...