CVE-2026-57173
vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions
Impact
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.
Affected packages
| Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|
| pip | vllm | <= 0.23.0 | 0.24.0 |
Affected products
| Vendor | Product | Affected versions |
|---|---|---|
| Vllm | Vllm | before 0.24.0 |
Weakness classification
References
- NVD record
- CVE.org record
- GitHub advisory
- https://github.com/advisories/GHSA-hcwq-8wjf-3gcr
- https://github.com/vllm-project/vllm/security/advisories/GHSA-hcwq-8wjf-3gcr
- https://nvd.nist.gov/vuln/detail/CVE-2026-57173
- https://github.com/vllm-project/vllm/pull/45908
- https://github.com/vllm-project/vllm/commit/3d20275bb4d434f53055c3c0b645fd8bb072965e
- https://github.com/vllm-project/vllm/releases/tag/v0.24.0