CVE-2026-105758 · GHSA-x6mc-67gf-chw4
vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach
- Risk score
- 41/100
- CVSS
- 5.3 v3.1
- Exploit chance (30 days)
- 0.3%
- Published
- 5 Oct 2026
Open in the live forecast Today's forecast
What to know
- What it is
- 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 media_io_kwargs.video.max_frames and media_io_kwargs.video.fps fields without enforcing server-side ceilings. An unauthenticated calle…
- Affected
- vllm (pip) >= 0.24.0, < 0.30.0
- Fix
- Upgrade vllm to 0.30.0 or later.
- Exploitation
- No known exploitation
Story map
At a glance
Vllm: Amber, patch this week. vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA ten…
The flaws
- CVE-2026-105758: VLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach (CVSS 5.3 · EPSS 0%)
- CVE-2026-100652: Improper input validation (CVSS 7.5 · EPSS 0%)
- CVE-2026-105759: VLLM is an inference and serving engine for large language models (CVSS 7.5 · EPSS 0%)
- CVE-2026-103241: Denial of service (CVSS 7.5 · EPSS 1%)
The fix
Upgrade Vllm: 0.30.0 or later on your release line
Who is exposed: Vllm
Where it stands
- Public proof of concept
Connects to
- Same weakness: Denial of service (CWE-770). 202 other warnings in 30 days
- Same product: Earlier vllm warnings. 15 in the last 90 days
Why it is Yellow
- CVSS 5.3 medium
- On your watchlist: PyPI
Affected packages
| Package | Ecosystem | Vulnerable | Fixed in |
|---|---|---|---|
| vllm | pip | >= 0.24.0, < 0.30.0 | 0.30.0 |
References
- https://github.com/advisories/GHSA-x6mc-67gf-chw4
- https://github.com/vllm-project/vllm/security/advisories/GHSA-x6mc-67gf-chw4
- https://github.com/vllm-project/vllm/pull/56729
- https://github.com/vllm-project/vllm/commit/ea723c81c3ea26425cb69503a5d5e90822a04a45
- https://github.com/vllm-project/vllm/releases/tag/v0.30.0
- https://github.com/advisories/GHSA-x6mc-67gf-chw4
Original description
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 media_io_kwargs.video.max_frames and media_io_kwargs.video.fps fields without enforcing server-side ceilings. An unauthenticated caller can submit these values to the /tokenize endpoint, causing the sampler to decode every frame selected from attacker-controlled video input, consume disproportionate frontend memory, and potentially terminate the API process before scheduling or admission control. The Rust frontend is not affected because it rejects the media_io_kwargs field. This issue is fixed in version 0.30.0.
Last activity 5 Oct 2026. Patch Forecast updates every hour.