CVE-2026-94627

vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child requests share a single transfer ID in prefill/decode disaggregated deployments. Attackers can trigger GPU memory exhaustion by submitting completion requests with multiple prompts,...

CVE-2026-94627 vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision

vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child requests share a single transfer ID in prefill/decode disaggregated deployments. Attackers can trigger GPU memory exhaustion by submitting completion requests with multiple prompts,...

CVE-2026-94627

vLLM Mooncake connector (through version 0.29.0) fails to properly manage GPU KV cache block ownership when concurrent child requests share a single transfer ID in prefill/decode disaggregated deployments. An unauthenticated remote attacker can trigger GPU memory exhaustion by submitting completi...

SUSE CVE-2026-90239

In the Linux kernel, the following vulnerability has been resolved: media: amd: isp4: release partial allocations in isp4ifallocfwgpumem isp4ifallocfwgpumem allocates several GPU memory pools in sequence. If one of them fails, it jumps to errornomemory and returns -ENOMEM without releasing the...

PT-2026-96317

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.29.1 Description The Mooncake connector fails to properly manage GPU KV cache block ownership during prefill/decode disaggregated deployments when concurrent child requests share a single transfer ID. An attacker can...

Linux Distros Unpatched Vulnerability : CVE-2026-90239

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: media: amd: isp4: release partial allocations in isp4ifallocfwgpumem isp4ifallocfwgpumem...

EUVD-2026-80935

vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation...

CVE-2026-90239

In the Linux kernel, the following vulnerability has been resolved: media: amd: isp4: release partial allocations in isp4ifallocfwgpumem isp4ifallocfwgpumem allocates several GPU memory pools in sequence. If one of them fails, it jumps to errornomemory and returns -ENOMEM without releasing the...

CVE-2026-90239 media: amd: isp4: release partial allocations in isp4if_alloc_fw_gpumem()

In the Linux kernel, the following vulnerability has been resolved: media: amd: isp4: release partial allocations in isp4ifallocfwgpumem isp4ifallocfwgpumem allocates several GPU memory pools in sequence. If one of them fails, it jumps to errornomemory and returns -ENOMEM without releasing the...

PT-2026-94587

Name of the Vulnerable Software and Affected Versions Linux kernel affected versions not specified Description A memory leak occurs in the isp4if alloc fw gpumem function when allocating GPU memory pools in sequence. If an allocation fails, the system jumps to error no memory and returns -ENOMEM...

CVE-2026-69147

A flaw was found in vLLM, an inference and serving engine for large language models. An attacker can exploit this by submitting specially crafted video requests that force the use of the PyNvVideoCodec GPU decoder. This bypasses the engine's static GPU memory reservation, allowing the attacker to...

CVE-2026-69147

vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set mediaiokwargs.video.videobackend to pynvvideocodec, and MediaConnector.fetchvideo forwards that choice to VideoMediaIO even when startup configuration...

CVE-2026-69147

vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set mediaiokwargs.video.videobackend to pynvvideocodec, and MediaConnector.fetchvideo forwards that choice to VideoMediaIO even when startup configuration...

CVE-2026-69147 vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation

vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set mediaiokwargs.video.videobackend to pynvvideocodec, and MediaConnector.fetchvideo forwards that choice to VideoMediaIO even when startup configuration...

PT-2026-93891

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.28.0 Description An issue exists where the engine fails to properly budget GPU memory when a user specifies a GPU decoder at request time. Specifically, request bodies for Chat Completions and Responses can set media i...

CVE-2026-9040

A race condition vulnerability in Arm Ltd Bifrost GPU Kernel Driver, Arm Ltd Valhall GPU Kernel Driver, Arm Ltd Arm 5th Gen GPU Architecture Kernel Driver allows a local non-privileged user process to perform improper GPU memory processing operations to cause a denial of service or disclose...

CVE-2026-7476

Use After Free vulnerability in Arm Ltd Bifrost GPU Kernel Driver, Arm Ltd Valhall GPU Kernel Driver, Arm Ltd Arm 5th Gen GPU Architecture Kernel Driver allows a local non-privileged user process to perform improper GPU memory processing operations to access already freed memory. This issue affec...

CVE-2026-0860

Exposure of Sensitive Information to an Unauthorized Actor vulnerability in Arm Ltd Valhall GPU Kernel Driver, Arm Ltd Arm 5th Gen GPU Architecture Kernel Driver allows a local non-privileged user process to perform improper GPU memory processing operations to gain access to sensitive kernel...

CVE-2026-12285

A Use After Free vulnerability exists in several Arm Ltd GPU kernel drivers, including the Bifrost , Valhall , and Arm 5th Gen GPU Architecture drivers. This flaw allows a local non-privileged user process to perform valid GPU memory processing operations to access memory that has already been fr...

EUVD-2026-72800

A race condition vulnerability in Arm Ltd Bifrost GPU Kernel Driver, Arm Ltd Valhall GPU Kernel Driver, Arm Ltd Arm 5th Gen GPU Architecture Kernel Driver allows a local non-privileged user process to perform improper GPU memory processing operations to cause a denial of service or disclose...