EUVD-2026-60565

A security vulnerability has been detected in sonos tract up to 0.23.4. This impacts the function Tensor::fromrawdtalign of the file data/src/tensor.rs of the component ONNX Initializer Loader. Such manipulation leads to incorrect calculation of buffer size. The attack may be launched remotely. T...

PT-2026-76902

A security vulnerability has been detected in sonos tract up to 0.23.4. This impacts the function Tensor::from raw dt align of the file data/src/tensor.rs of the component ONNX Initializer Loader. Such manipulation leads to incorrect calculation of buffer size. The attack may be launched remotely...

CVE-2026-75093: Incorrect Calculation of Buffer Size

A security vulnerability has been detected in sonos tract up to 0.23.4. This impacts the function Tensor::fromrawdtalign of the file data/src/tensor.rs of the component ONNX Initializer Loader. Such manipulation leads to incorrect calculation of buffer size. The attack may be launched remotely. T...

SUSE CVE-2026-73557

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...

Race Condition

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Race Condition through the safeloadpromptembeds function in vllm/renderers/embedutils.py when concurrent prompt parts are submitted to the...

CVE-2026-73557

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...

CVE-2026-73557

CVE-2026-73557 affects vLLM between 0.20.2rc0 and 0.26.0. The flaw arises in safe_load_prompt_embeds in vllm/renderers/embed_utils.py, where using torch.sparse.check_sparse_tensor_invariants with a process-global save/enable/restore state can be raced via concurrent prompt_embeds (POST /v1/chat/c...

CVE-2026-73557 vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...

CVE-2026-73557

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...

PT-2026-71672

Name of the Vulnerable Software and Affected Versions vLLM versions 0.20.2rc0 through 0.25.x Description A race condition exists in the safe load prompt embeds function within vllm/renderers/embed utils.py when enable prompt embeds is enabled. The issue occurs because torch.sparse.check sparse...

Out-of-bounds Read

Overview Affected versions of this package are vulnerable to Out-of-bounds Read in the adaptgemm76 function when processing input tensors with fewer than two dimensions. An attacker can cause a crash or potentially leak adjacent heap memory by providing a specially crafted model file with...

CVE-2026-65918

PyTorch torchvision through 0.28.0, fixed in commit 4e05dc2, contains an out-of-bounds heap read vulnerability in the GIF decoder's readfromtensor callback that passes unclamped length to memcpy. Attackers can supply malicious or truncated GIF files to cause denial of service via segmentation fau...

CVE-2026-47470

NVIDIA TensorRT-LLM for any platform contains a vulnerability in the gRPC server chat API endpoint, where an attacker could cause CWE-20 by local attack. A successful exploit of this vulnerability might lead to denial of service...

EUVD-2026-44468

NVIDIA TensorRT-LLM for any platform contains a vulnerability in the gRPC server chat API endpoint, where an attacker could cause CWE-20 by local attack. A successful exploit of this vulnerability might lead to denial of service...

CVE-2026-47471

NVIDIA TensorRT-LLM for any platform contains a vulnerability in tensor deserialization, where an attacker could cause a heap based buffer overflow. A successful exploit of this vulnerability might lead to information disclosure, data tampering, or denial of service...

CVE-2026-47471

NVIDIA TensorRT-LLM for any platform contains a vulnerability in tensor deserialization, where an attacker could cause a heap based buffer overflow. A successful exploit of this vulnerability might lead to information disclosure, data tampering, or denial of service...

EUVD-2026-44451

NVIDIA TensorRT-LLM for any platform contains a vulnerability in tensor deserialization, where an attacker could cause a heap based buffer overflow. A successful exploit of this vulnerability might lead to information disclosure, data tampering, or denial of service...

CVE-2026-47471

NVIDIA TensorRT-LLM (any platform) is reported vulnerable to a heap-based buffer overflow in tensor deserialization (CVE-2026-47471). Affected component: TensorRT-LLM’s tensor deserialization pathway. Consequences described: information disclosure, data tampering, and denial of service. Exploitat...

PT-2026-58754

NVIDIA TensorRT-LLM for any platform contains a vulnerability in tensor deserialization, where an attacker could cause a heap based buffer overflow. A successful exploit of this vulnerability might lead to information disclosure, data tampering, or denial of service...

CVE-2026-47471: Heap-based Buffer Overflow

NVIDIA TensorRT-LLM for any platform contains a vulnerability in tensor deserialization, where an attacker could cause a heap based buffer overflow. A successful exploit of this vulnerability might lead to information disclosure, data tampering, or denial of service...