PYSEC-2026-3403 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...

PYSEC-2026-3271 TensorFlow has Null Pointer Error in QuantizedMatMulWithBiasAndDequantize

Impact NPE in QuantizedMatMulWithBiasAndDequantize with MKL enable python import tensorflow as tf func = tf.rawops.QuantizedMatMulWithBiasAndDequantize para='a': tf.constant138, dtype=tf.quint8, 'b': tf.constant4, dtype=tf.qint8, 'bias': 31.81644630432129, 47.21876525878906, 109.95201110839844,...

PYSEC-2026-3098 TensorFlow has Null Pointer Error in QuantizedMatMulWithBiasAndDequantize

Impact NPE in QuantizedMatMulWithBiasAndDequantize with MKL enable python import tensorflow as tf func = tf.rawops.QuantizedMatMulWithBiasAndDequantize para='a': tf.constant138, dtype=tf.quint8, 'b': tf.constant4, dtype=tf.qint8, 'bias': 31.81644630432129, 47.21876525878906, 109.95201110839844,...

PYSEC-2026-3323 Heap overflow in `QuantizeAndDequantizeV2`

Impact The function MakeGrapplerFunctionItem takes arguments that determine the sizes of inputs and outputs. If the inputs given are greater than or equal to the sizes of the outputs, an out-of-bounds memory read or a crash is triggered. python import tensorflow as tf @tf.function def test:...

PYSEC-2026-3178 Heap overflow in `QuantizeAndDequantizeV2`

Impact The function MakeGrapplerFunctionItem takes arguments that determine the sizes of inputs and outputs. If the inputs given are greater than or equal to the sizes of the outputs, an out-of-bounds memory read or a crash is triggered. python import tensorflow as tf @tf.function def test:...

PYSEC-2026-3149 TensorFlow vulnerable to `CHECK` fail in `QuantizeAndDequantizeV3`

Impact If QuantizeAndDequantizeV3 is given a nonscalar numbits input tensor, it results in a CHECK fail that can be used to trigger a denial of service attack. python import tensorflow as tf signedinput = True rangegiven = False narrowrange = False axis = -1 input = tf.constant-3.5, shape=1,...

PYSEC-2026-3304 TensorFlow vulnerable to `CHECK` fail in `QuantizeAndDequantizeV3`

Impact If QuantizeAndDequantizeV3 is given a nonscalar numbits input tensor, it results in a CHECK fail that can be used to trigger a denial of service attack. python import tensorflow as tf signedinput = True rangegiven = False narrowrange = False axis = -1 input = tf.constant-3.5, shape=1,...

PYSEC-2026-3334 Missing validation crashes `QuantizeAndDequantizeV4Grad`

Impact The implementation of tf.rawops.QuantizeAndDequantizeV4Grad 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 tf.rawops.QuantizeAndDequantizeV4Grad gradients=tf.constant1,...

PYSEC-2026-3195 Missing validation crashes `QuantizeAndDequantizeV4Grad`

Impact The implementation of tf.rawops.QuantizeAndDequantizeV4Grad 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 tf.rawops.QuantizeAndDequantizeV4Grad gradients=tf.constant1,...

PYSEC-2026-3082 Out of bounds read in Tensorflow

Impact The implementation of Dequantize does not fully validate the value of axis and can result in heap OOB accesses: python import tensorflow as tf @tf.function def test: y = tf.rawops.Dequantize input=tf.constant1,1,dtype=tf.qint32, minrange=1.0, maxrange=10.0, mode='MINCOMBINED',...

PYSEC-2026-3159 Integer overflow in Tensorflow

Impact The implementation of shape inference for Dequantize is vulnerable to an integer overflow weakness: python import tensorflow as tf input = tf.constant1,1,dtype=tf.qint32 @tf.function def test: y = tf.rawops.Dequantize input=input, minrange=1.0, maxrange=10.0, mode='MINCOMBINED',...

PYSEC-2026-1955 TensorFlow has Null Pointer Error in QuantizedMatMulWithBiasAndDequantize

Impact NPE in QuantizedMatMulWithBiasAndDequantize with MKL enable python import tensorflow as tf func = tf.rawops.QuantizedMatMulWithBiasAndDequantize para='a': tf.constant138, dtype=tf.quint8, 'b': tf.constant4, dtype=tf.qint8, 'bias': 31.81644630432129, 47.21876525878906, 109.95201110839844,...

PYSEC-2026-992 Heap overflow in `QuantizeAndDequantizeV2`

Impact The function MakeGrapplerFunctionItem takes arguments that determine the sizes of inputs and outputs. If the inputs given are greater than or equal to the sizes of the outputs, an out-of-bounds memory read or a crash is triggered. python import tensorflow as tf @tf.function def test:...

PYSEC-2026-976 TensorFlow vulnerable to `CHECK` fail in `QuantizeAndDequantizeV3`

Impact If QuantizeAndDequantizeV3 is given a nonscalar numbits input tensor, it results in a CHECK fail that can be used to trigger a denial of service attack. python import tensorflow as tf signedinput = True rangegiven = False narrowrange = False axis = -1 input = tf.constant-3.5, shape=1,...

PYSEC-2026-1002 Missing validation crashes `QuantizeAndDequantizeV4Grad`

Impact The implementation of tf.rawops.QuantizeAndDequantizeV4Grad 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 tf.rawops.QuantizeAndDequantizeV4Grad gradients=tf.constant1,...

PYSEC-2026-549 TensorFlow has a heap out-of-buffer read vulnerability in the QuantizeAndDequantize operation

Impact Attackers using Tensorflow can exploit the vulnerability. They can access heap memory which is not in the control of user, leading to a crash or RCE. When axis is larger than the dim of input, c-Diminput,axis goes out of bound. Same problem occurs in the QuantizeAndDequantizeV2/V3/V4/V4Gra...

PYSEC-2026-548 TensorFlow has a heap out-of-buffer read vulnerability in the QuantizeAndDequantize operation

Impact Attackers using Tensorflow can exploit the vulnerability. They can access heap memory which is not in the control of user, leading to a crash or RCE. When axis is larger than the dim of input, c-Diminput,axis goes out of bound. Same problem occurs in the QuantizeAndDequantizeV2/V3/V4/V4Gra...

PYSEC-2026-550 TensorFlow has a heap out-of-buffer read vulnerability in the QuantizeAndDequantize operation

Impact Attackers using Tensorflow can exploit the vulnerability. They can access heap memory which is not in the control of user, leading to a crash or RCE. When axis is larger than the dim of input, c-Diminput,axis goes out of bound. Same problem occurs in the QuantizeAndDequantizeV2/V3/V4/V4Gra...

CVE-2026-53923

A flaw was found in vLLM. Integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels leads to partial tensor processing. This results in the output tensor retaining previously used GPU memory, which, in multi-tenant inference deployments, can expose sensitive tensor data from other...

CVE-2026-53923

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/ggufkernel.cu causes partial tensor processing. The output tensor is allocated at full size via...