vLLM 0.25.0 before 0.31.0 MOSS-Audio Memory Exhaustion via /tokenize mm_processor_kwargs
Get instant alerts when new vulnerabilities affect vllm - before attackers find them.
vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches a processor for every distinct request-controlled mm_processor_kwargs value in an unbounded dictionary. Unauthenticated attackers can send distinct or oversized mel_config values to the /tokenize endpoint, which bypasses --api-key, to exhaust host memory and crash the API process.
No remediation guidance has been written for this CVE yet. What the record does show:
Patch and advisory references
SSVC signals action urgency (what to patch first), separate from CVSS which measures severity.
Get alerted
Track the products you run and VulnTracker tells you when a new CVE affects them — with what is known about fixing it, and nothing about the rest.