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 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

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...

EUVD-2026-58064

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

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safe load prompt embeds in vllm/renderers/embed utils.py uses torch.sparse.check sparse tensor invariants, whose process-global save, enable, and restore state can be raced by concurrent prompt embeds...

PYSEC-2026-3365 Missing validation results in undefined behavior in `SparseTensorDenseAdd

Impact The implementation of tf.rawops.SparseTensorDenseAdd does not fully validate the input arguments: python import tensorflow as tf aindices = tf.constant0, shape=17, 2, dtype=tf.int64 avalues = tf.constant, shape=0, dtype=tf.float32 ashape = tf.constant6, 12, shape=2, dtype=tf.int64 b =...

PYSEC-2026-3235 Missing validation results in undefined behavior in `SparseTensorDenseAdd

Impact The implementation of tf.rawops.SparseTensorDenseAdd does not fully validate the input arguments: python import tensorflow as tf aindices = tf.constant0, shape=17, 2, dtype=tf.int64 avalues = tf.constant, shape=0, dtype=tf.float32 ashape = tf.constant6, 12, shape=2, dtype=tf.int64 b =...

PYSEC-2026-3214 Missing validation causes denial of service via `SparseTensorToCSRSparseMatrix`

Impact The implementation of tf.rawops.SparseTensorToCSRSparseMatrix does not fully validate the input arguments. This results in a CHECK-failure which can be used to trigger a denial of service attack: python import tensorflow as tf indices = tf.constant53, shape=3, dtype=tf.int64 values =...

PYSEC-2026-3350 Missing validation causes denial of service via `SparseTensorToCSRSparseMatrix`

Impact The implementation of tf.rawops.SparseTensorToCSRSparseMatrix does not fully validate the input arguments. This results in a CHECK-failure which can be used to trigger a denial of service attack: python import tensorflow as tf indices = tf.constant53, shape=3, dtype=tf.int64 values =...

PYSEC-2026-3223 Undefined behavior in `SparseTensorSliceDataset`

Impact The implementation of SparseTensorSliceDataset has an undefined behavior: under certain condition it can be made to dereference a nullptr value: python import tensorflow as tf import numpy as np tf.rawops.SparseTensorSliceDataset indices=, values=, denseshape=1,1 The 3 input arguments...

PYSEC-2026-2018 vLLM deserialization vulnerability leading to DoS and potential RCE

Summary A memory corruption vulnerability that leading to a crash denial-of-service and potentially remote code execution RCE exists in vLLM versions 0.10.2 and later, in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using...

PYSEC-2026-947 TensorFlow vulnerable to segfault in `SparseBincount`

Impact If SparseBincount is given inputs for indices, values, and denseshape that do not make a valid sparse tensor, it results in a segfault that can be used to trigger a denial of service attack. python import tensorflow as tf binaryoutput = True indices = tf.random.uniformshape=, minval=-10000...

PYSEC-2026-1032 Missing validation results in undefined behavior in `SparseTensorDenseAdd

Impact The implementation of tf.rawops.SparseTensorDenseAdd does not fully validate the input arguments: python import tensorflow as tf aindices = tf.constant0, shape=17, 2, dtype=tf.int64 avalues = tf.constant, shape=0, dtype=tf.float32 ashape = tf.constant6, 12, shape=2, dtype=tf.int64 b =...

PYSEC-2026-1018 Missing validation causes denial of service via `SparseTensorToCSRSparseMatrix`

Impact The implementation of tf.rawops.SparseTensorToCSRSparseMatrix does not fully validate the input arguments. This results in a CHECK-failure which can be used to trigger a denial of service attack: python import tensorflow as tf indices = tf.constant53, shape=3, dtype=tf.int64 values =...

PYSEC-2026-250

vLLM versions = 0.10.2 and 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed negative or out-of-bounds tensor indices, when the...

CVE-2026-56340 vLLM - Denial of Service via Unvalidated Multimodal Embeddings

vLLM versions = 0.10.2 and 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed negative or out-of-bounds tensor indices, when the...

CVE-2026-56340

vLLM versions = 0.10.2 and 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed negative or out-of-bounds tensor indices, when the...

CVE-2026-56340 vLLM - Denial of Service via Unvalidated Multimodal Embeddings

vLLM versions = 0.10.2 and 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed negative or out-of-bounds tensor indices, when the...

CVE-2026-56340 vLLM - Denial of Service via Unvalidated Multimodal Embeddings

vLLM versions = 0.10.2 and 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed negative or out-of-bounds tensor indices, when the...