CVE-2026-55646
vLLM is an inference and serving engine for large language models. …
vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read() to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed upload size limit (default 25 MB) later in the speech-to-text preprocessing step, so an API caller who can reach those routes can submit an oversized multipart upload and cause vLLM to allocate memory proportional to the uploaded file size before the request is rejected as too large, creating memory pressure or terminating the process depending on deployment resource limits. 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/b997071ec493765abbed990c65843ed05e4708a8
- github.com/vllm-project/vllm/pull/45510
- github.com/vllm-project/vllm/security/advisories/GHSA-v82g-2437-67m2
- nvd.nist.gov/vuln/detail/CVE-2026-55646
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2305.yaml
- github.com/advisories/GHSA-v82g-2437-67m2
- nvd.nist.gov/vuln/detail/CVE-2026-55646
- cve.org/CVERecord?id=CVE-2026-55646
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.