CVE-2026-57173
vLLM is an inference and serving engine for large language models. …
vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the input_audio handling path for /v1/chat/completions calls AudioMediaIO.load_bytes or AudioMediaIO.load_file without passing VLLM_MAX_AUDIO_DECODE_DURATION_S to the shared audio decoder. An unauthenticated client can therefore submit a small compressed audio input that expands into a very large float32 PCM allocation, bypassing the duration guard already used by /v1/audio/transcriptions and causing an out-of-memory worker crash. Inline data URLs reach this path without being bounded by VLLM_AUDIO_FETCH_TIMEOUT. The issue affects deployments serving an audio-capable model, and authentication changes only the deployment-specific reachability. This issue is fixed in version 0.24.0.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/vllm-project/vllm/commit/3d20275bb4d434f53055c3c0b645fd8bb072965e
- github.com/vllm-project/vllm/pull/45908
- github.com/vllm-project/vllm/releases/tag/v0.24.0
- github.com/vllm-project/vllm/security/advisories/GHSA-hcwq-8wjf-3gcr
- nvd.nist.gov/vuln/detail/CVE-2026-57173
- github.com/advisories/GHSA-hcwq-8wjf-3gcr
- nvd.nist.gov/vuln/detail/CVE-2026-57173
- cve.org/CVERecord?id=CVE-2026-57173
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.