PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-57173 vllm-project CVE debrief

CVE-2026-57173 is a vulnerability in the vLLM inference and serving engine for large language models. The input_audio handling path for /v1/chat/completions calls in vLLM prior to 0.24.0 can lead to an out-of-memory worker crash due to a small compressed audio input expanding into a large float32 PCM allocation. This issue affects deployments serving an audio-capable model. The vulnerability is fixed in version 0.24.0. Defenders of vLLM deployments serving audio-capable models should assess exposure and prioritize upgrading to version 0.24.0 or later to prevent potential out-of-memory worker crashes. The CVE record and NVD vulnerability detail page provide additional information on

Vendor
vllm-project
Product
vllm
CVSS
MEDIUM 6.5
CISA KEV
Not listed in stored evidence
Original CVE published
2026-09-16
Original CVE updated
2026-09-18
Advisory published
2026-09-16
Advisory updated
2026-09-18

Who should care

Defenders of vLLM deployments serving audio-capable models should assess exposure and prioritize upgrading to version 0.24.0 or later to prevent potential out-of-memory worker crashes.

Why it matters

CVE-2026-57173 is a vulnerability in the vLLM inference and serving engine for large language models, which can lead to an out-of-memory worker crash. Defenders of vLLM deployments serving audio-capable models should assess exposure and prioritize upgrading to version 0.24.0 or later.

  • Potential out-of-memory worker crashes in vLLM deployments serving audio-capable models
  • Need to verify and update vLLM deployments to version 0.24.0 or later

Technical summary

The input_audio handling path for /v1/chat/completions calls in vLLM prior to 0.24.0 can lead to an out-of-memory worker crash due to a small compressed audio input expanding into a large float32 PCM allocation. This issue affects deployments serving an audio-capable model. The vulnerability is fixed in version 0.24.0. Defenders should prioritize upgrading to version 0.24.0 or later to prevent potential out-of-memory worker crashes in vLLM deployments serving audio-capable models. The vulnerability detail includes information on the AudioMediaIO.load_bytes or AudioMediaIO.load_file without passing VLLM_MAX_AUDIO_DECODE_DURATION_S to the shared audio decoder.

Defensive priority

Defenders should prioritize upgrading to version 0.24.0 or later to prevent potential out-of-memory worker crashes in vLLM deployments serving audio-capable models.

Recommended defensive actions

  • Upgrade to version 0.24.0 or later
  • Review and update vLLM deployments serving audio-capable models
  • Monitor for potential out-of-memory worker crashes
  • Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up
  • Review compensating controls for exposed systems while remediation is scheduled and verified
  • Check relevant monitoring, detection, and logs for exposed assets that need extra review
  • Track exceptions, retest remediated assets, and close the item only after evidence is documented

Evidence notes

The CVE record and NVD vulnerability detail page provide information on the vulnerability, its impact, and the fixed version. The input_audio handling path for /v1/chat/completions calls in vLLM prior to 0.24.0 can lead to an out-of-memory worker crash due to a small compressed audio input expanding into a large float32 PCM allocation. This issue affects deployments serving an audio-capable model. Defenders should verify and update vLLM deployments to version 0.24.0 or later. The vulnerability detail includes information on the Audio

Sources and references

Verified primary and authoritative sources

  • CVE-2026-57173 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-57173

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-57173 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-57173

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.