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...

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...

libvpx:vpx_enc_fuzzer_vp8_nalloc: Use-of-uninitialized-value in vp8_regular_quantize_b_sse4_1

Project: https://chromium.googlesource.com/webm/libvpx Detailed Report: https://oss-fuzz.com/testcase?key=4581817557778432 Project: libvpx Fuzzing Engine: libFuzzer Fuzz Target: vpxencfuzzervp8nalloc Job Type: libfuzzermsanlibvpx Platform Id: linux Crash Type: Use-of-uninitialized-value Crash...

Widening the Gap: Exploiting LLM Quantization Via Outlier Injection

LLM quantization has become essential for memory-efficient deployment. Recent work has shown that quantization schemes can pose critical security risks: an adversary may release a model that appears benign in full precision but exhibits malicious behavior once quantized by users. However, existin...

Exploit for CVE-2026-7482

CVE-2026-7482: Ollama Heap Out-of-Bounds Read 1-Day PoC Thi...

CVE-2026-7482: Out-of-bounds Read

Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and...

PT-2026-34454

Name of the Vulnerable Software and Affected Versions Ollama affected versions not specified Description An out-of-bounds memory read and write issue exists in the GGUF GPT-Generated Unified Format quantization engine. This occurs because the engine lacks proper bounds checking and trusts tensor...

Ollama GGUF Quantization Remote Memory Leak

Overview Ollama’s model quantization engine contains a vulnerability that allows an attacker with access to the model upload interface to read and potentially exfiltrate heap memory from the server. This issue may lead to unintended behavior, including unauthorized access to sensitive data and, i...

CVE-2025-33247

NVIDIA Megatron LM contains a vulnerability in quantization configuration loading, which could allow remote code execution. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, information disclosure, and data tampering...

CVE-2026-24141

NVIDIA Model Optimizer for Windows and Linux contains a vulnerability in the ONNX quantization feature, where a user could cause unsafe deserialization by providing a specially crafted input file. A successful exploit of this vulnerability might lead to code execution, escalation of privileges,...

turboquant-monitoring-poc

TurboQuant x WhatAp Monitoring POC TurboQuanthttps://arxiv...

Deserialization of Untrusted Data

Overview megatron-core is a Megatron Core - a library for efficient and scalable training of transformer based models Affected versions of this package are vulnerable to Deserialization of Untrusted Data in the quantization configuration loading process. An attacker can execute arbitrary code,...

EUVD-2025-208974

NVIDIA Megatron LM contains a vulnerability in quantization configuration loading, which could allow remote code execution. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, information disclosure, and data tampering...

CVE-2026-24141

NVIDIA Model Optimizer for Windows and Linux contains a vulnerability in the ONNX quantization feature, where a user could cause unsafe deserialization by providing a specially crafted input file. A successful exploit of this vulnerability might lead to code execution, escalation of privileges,...

CVE-2025-33247

NVIDIA Megatron LM contains a vulnerability in quantization configuration loading, which could allow remote code execution. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, information disclosure, and data tampering...

CVE-2026-24141

CVE-2026-24141 affects NVIDIA Model Optimizer for Windows and Linux, where the ONNX quantization feature allows unsafe deserialization via a crafted input file. This can lead to code execution, escalation of privileges, data tampering, and information disclosure. NVIDIA states affected versions a...

CVE-2026-24141

NVIDIA Model Optimizer for Windows and Linux contains a vulnerability in the ONNX quantization feature, where a user could cause unsafe deserialization by providing a specially crafted input file. A successful exploit of this vulnerability might lead to code execution, escalation of privileges,...

CVE-2026-24141

NVIDIA Model Optimizer for Windows and Linux contains a vulnerability in the ONNX quantization feature, where a user could cause unsafe deserialization by providing a specially crafted input file. A successful exploit of this vulnerability might lead to code execution, escalation of privileges,...

CVE-2025-33247

NVIDIA Megatron LM contains a vulnerability in quantization configuration loading, which could allow remote code execution. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, information disclosure, and data tampering...

CVE-2025-33247

NVIDIA Megatron LM is affected by CVE-2025-33247 due to a vulnerability in quantization configuration loading that could allow remote code execution. The security bulletin states this could lead to code execution, elevation of privileges, information disclosure, and data tampering. Affected produ...