CVE-2026-116179

vLLM from 0.18.0 before 0.31.0 contains a resource exhaustion vulnerability that allows API clients to bypass the video/jpeg frame-count cap by overriding numframes through mediaiokwargs. Attackers can set numframes to -1 with a large inline video so VideoMediaIO.loadbase64 decodes every frame,...

CVE-2026-116179 vLLM 0.18.0 before 0.31.0 Memory Exhaustion via media_io_kwargs num_frames Override

vLLM from 0.18.0 before 0.31.0 contains a resource exhaustion vulnerability that allows API clients to bypass the video/jpeg frame-count cap by overriding numframes through mediaiokwargs. Attackers can set numframes to -1 with a large inline video so VideoMediaIO.loadbase64 decodes every frame,...

CVE-2026-116179 vLLM 0.18.0 before 0.31.0 Memory Exhaustion via media_io_kwargs num_frames Override

vLLM from 0.18.0 before 0.31.0 contains a resource exhaustion vulnerability that allows API clients to bypass the video/jpeg frame-count cap by overriding numframes through mediaiokwargs. Attackers can set numframes to -1 with a large inline video so VideoMediaIO.loadbase64 decodes every frame,...

CVE-2026-116179

The vLLM library, versions 0.18.0 before 0.31.0 , is susceptible to a memory exhaustion vulnerability. An attacker can bypass the video/jpeg frame-count cap by overriding the num_frames parameter through media_io_kwargs. By setting num_frames to -1 while providing a large inline video, the VideoM...

CVE-2026-116179

vLLM from 0.18.0 before 0.31.0 contains a resource exhaustion vulnerability that allows API clients to bypass the video/jpeg frame-count cap by overriding numframes through mediaiokwargs. Attackers can set numframes to -1 with a large inline video so VideoMediaIO.loadbase64 decodes every frame,...

EUVD-2026-109440

vLLM from 0.18.0 before 0.31.0 contains a resource exhaustion vulnerability that allows API clients to bypass the video/jpeg frame-count cap by overriding numframes through mediaiokwargs. Attackers can set numframes to -1 with a large inline video so VideoMediaIO.loadbase64 decodes every frame,...

CVE-2026-116179 vLLM 0.18.0 before 0.31.0 Memory Exhaustion via media_io_kwargs num_frames Override

vLLM from 0.18.0 before 0.31.0 contains a resource exhaustion vulnerability that allows API clients to bypass the video/jpeg frame-count cap by overriding numframes through mediaiokwargs. Attackers can set numframes to -1 with a large inline video so VideoMediaIO.loadbase64 decodes every frame,...

vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion

SummaryThe OpenAI-compatible chat endpoint accepts request-level video loader options through mediaiokwargs. A caller can select the GLMGA sampler and provide large fps and maxframes values. GLMGA first constructs an attacker-sized Python index list and then deduplicates it, even when the supplie...

PYSEC-2026-4307 vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion

Summary The OpenAI-compatible chat endpoint accepts request-level video loader options through mediaiokwargs. A caller can select the GLMGA sampler and provide large fps and maxframes values. GLMGA first constructs an attacker-sized Python index list and then deduplicates it, even when the suppli...

WS-2026-0137

vllm 0.18.0 - 0.30.0: request-level mediaiokwargs can set video numframes to -1 or any size, bypassing the frame-count cap in VideoMediaIO.loadbase64 for inline video/jpeg and letting a client exhaust API-server memory GHSA-4m6g-h9mv-wqjc...

EUVD-2026-92848

vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled maxframes, which the numframes ceiling does not reach...

GHSA-58V5-2M8F-94PR vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion

Summary The OpenAI-compatible chat endpoint accepts request-level video loader options through mediaiokwargs. A caller can select the GLMGA sampler and provide large fps and maxframes values. GLMGA first constructs an attacker-sized Python index list and then deduplicates it, even when the suppli...

EUVD-2026-92851

vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion...

CVE-2026-105758

vLLM is an inference and serving engine for large language models. From 0.24.0 until 0.30.0, the Qwen2VLVideoBackend and Qwen3VLVideoBackend classes accept request-level values for the mediaiokwargs.video.maxframes and mediaiokwargs.video.fps fields without enforcing server-side ceilings. An...

CVE-2026-105760

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level mediaiokwargs field to select the GLMGA video backend and supply large values for the fps and maxframes options without a strict work ceiling. GLMGA constructs and deduplicates a...

CVE-2026-105760

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level mediaiokwargs field to select the GLMGA video backend and supply large values for the fps and maxframes options without a strict work ceiling. GLMGA constructs and deduplicates a...

CVE-2026-105760 vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level mediaiokwargs field to select the GLMGA video backend and supply large values for the fps and maxframes options without a strict work ceiling. GLMGA constructs and deduplicates a...

CVE-2026-105760 vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level mediaiokwargs field to select the GLMGA video backend and supply large values for the fps and maxframes options without a strict work ceiling. GLMGA constructs and deduplicates a...

CVE-2026-105760 vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level mediaiokwargs field to select the GLMGA video backend and supply large values for the fps and maxframes options without a strict work ceiling. GLMGA constructs and deduplicates a...

CVE-2026-105760

The vLLM inference and serving engine for large language models is vulnerable to CPU and memory exhaustion in versions prior to 0.30.0 . An attacker can use the media_io_kwargs field to select the GLMGA video backend and provide large values for the fps and max_frames options. Because there is no...