Lucene search
+L

231 matches found

Kitploit
Kitploit
•added 2026/09/28 6:22 a.m.•13 views

EntropicaPublic

March updates I need to move some work over from the private repos. The exploration into using massivly multheaded models with mixer and readout functions separated continues. Currently training up a Chinese TinyStories on a 3B-equivalent model that trains, easily, on an 8GB gpu. We're looking at...

5.8AI score
SaveExploits0References4
Kitploit
Kitploit
•added 2026/09/27 5:17 a.m.•16 views

CVE-2025-14174-analysis

CVE-2025-14174 Analysis: ANGLE Metal Staging Buffer Out-of-Bounds Write Technical analysis and proof-of-concept for CVE-2025-14174 | ---|--- CVE| CVE-2025-14174 Severity| High Exploited ITW| Yes - targeted attacks on iOS 26 Affected| iOS Safari, macOS Chrome/Chromium/Electron not macOS Safari...

8.8CVSS8.3AI score0.22327EPSS
SaveExploits10
RedhatCVE
RedhatCVE
•added 2026/09/26 2:16 p.m.•9 views

CVE-2026-100649

A flaw was found in vLLM. An unauthenticated remote attacker can cause a Denial of Service DoS by submitting video processing requests that specify different sampler subclasses. Because active decoder counters are tracked independently across subclasses rather than globally, requests can bypass...

6.3CVSS5.8AI score0.0031EPSS
SaveExploits0References5
NVD
NVD
•added 2026/09/26 2:16 p.m.•9 views

CVE-2026-100649

vLLM before 0.29.0 contains a resource-limit bypass vulnerability in PyNvVideoCodec decoder allocation where sampler subclass shadowing allows independent counter increments. Unauthenticated attackers can select different sampler subclasses in video requests to exceed configured decoder limits an...

6.3CVSS0.0031EPSS
SaveExploits0References2
EUVD
EUVD
•added 2026/09/26 1:23 p.m.•7 views

EUVD-2026-87743

vLLM before 0.29.0 contains a resource-limit bypass vulnerability in PyNvVideoCodec decoder allocation where sampler subclass shadowing allows independent counter increments. Unauthenticated attackers can select different sampler subclasses in video requests to exceed configured decoder limits an...

6.3CVSS5.8AI score0.0031EPSS
SaveExploits0References2
Cvelist
Cvelist
•added 2026/09/26 1:23 p.m.•35 views

CVE-2026-100649 vLLM before 0.29.0 Resource Limit Bypass via Sampler Subclass

vLLM before 0.29.0 contains a resource-limit bypass vulnerability in PyNvVideoCodec decoder allocation where sampler subclass shadowing allows independent counter increments. Unauthenticated attackers can select different sampler subclasses in video requests to exceed configured decoder limits an...

6.3CVSS0.0031EPSS
SaveExploits0References2
OSV
OSV
•added 2026/09/26 1:23 p.m.•12 views

CVE-2026-100649 vLLM before 0.29.0 Resource Limit Bypass via Sampler Subclass

vLLM before 0.29.0 contains a resource-limit bypass vulnerability in PyNvVideoCodec decoder allocation where sampler subclass shadowing allows independent counter increments. Unauthenticated attackers can select different sampler subclasses in video requests to exceed configured decoder limits an...

6.3CVSS5.8AI score
SaveExploits0References4
CVE
CVE
•added 2026/09/26 1:23 p.m.•19 views

CVE-2026-100649

Versions of vLLM prior to 0.29.0 are vulnerable to a resource-limit bypass within the PyNvVideoCodec decoder allocation. The root cause is sampler subclass shadowing , which allows for independent counter increments rather than global tracking. An unauthenticated remote attacker can exploit this ...

6.3CVSS5.8AI score0.0031EPSS
SaveExploits0References2
RedhatCVE
RedhatCVE
•added 2026/09/22 4:44 p.m.•6 views

CVE-2026-94627

A flaw was found in vLLM. A remote attacker can exploit a vulnerability in the Mooncake connector's management of GPU Key-Value KV cache block ownership. By submitting completion requests with multiple prompts that share a single transfer ID, attackers can cause orphaned KV cache blocks to...

8.7CVSS5.8AI score0.0063EPSS
SaveExploits0References7
NVD
NVD
•added 2026/09/21 10:17 p.m.•11 views

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,...

8.7CVSS0.0063EPSS
SaveExploits0References4
CVE
CVE
•added 2026/09/21 10:04 p.m.•36 views

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...

8.7CVSS5.8AI score0.0063EPSS
SaveExploits0References4Affected Software1
Tenable Nessus
Tenable Nessus
•added 2026/09/18 12:00 a.m.•8 views

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...

5.8AI score0.00198EPSS
SaveExploits0References2
EUVD
EUVD
•added 2026/09/17 5:17 p.m.•11 views

EUVD-2026-80935

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

6.5CVSS5.8AI score0.00548EPSS
SaveExploits0References6
NVD
NVD
•added 2026/09/17 5:17 p.m.•8 views

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...

0.00198EPSS
SaveExploits0References2
Cvelist
Cvelist
•added 2026/09/17 4:07 p.m.•37 views

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...

0.00198EPSS
SaveExploits0References2
RedhatCVE
RedhatCVE
•added 2026/09/16 6:35 p.m.•11 views

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...

6.5CVSS5.8AI score0.00548EPSS
SaveExploits0References7
NVD
NVD
•added 2026/09/16 6:17 p.m.•10 views

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...

6.5CVSS0.00548EPSS
SaveExploits0References4
OSV
OSV
•added 2026/09/16 5:49 p.m.•7 views

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...

6.5CVSS5.8AI score
SaveExploits0References6
NVD
NVD
•added 2026/09/08 3:18 p.m.•18 views

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...

7.7CVSS0.00133EPSS
SaveExploits0References1
NVD
NVD
•added 2026/09/08 3:18 p.m.•17 views

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...

7.8CVSS0.00162EPSS
SaveExploits0References1
Rows per page
Query Builder