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...

CVE-2026-105760

A flaw was found in vLLM. A remote attacker can trigger a Denial of Service DoS by submitting a request with excessively large frame rate and frame count options for the GLMGA video backend. Because the application constructs intermediate frame index lists without proper upper bounds, processing...

EUVD-2026-92851

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

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...

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...

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

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...

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...

PT-2026-106272

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.30.0 Description A partial denial of service issue exists in the OpenAI-compatible chat endpoint. A remote caller can provide large values for the fps and max frames variables within the media io kwargs field while...

CVE-2026-105760: Uncontrolled Resource Consumption

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...