CVE-2026-100651: vLLM denial of service via overlong prompt on disaggregated generate endpoint

Summary

vLLM versions before 0.29.0 do not enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate when a request includes a 'features' multimodal payload. The GenerateRequest.token_ids list is not checked against model_config.max_model_len, and processors reporting skip_prompt_length_check=True (such as Nemotron Parse, Whisper, and FireRedLID) bypass validation entirely. A client that can reach the endpoint on an affected configuration can submit an overlong token_ids list and crash the worker, causing denial of service.

Mitigation

Fixed in 0.29.0.

Topics

• Inference infrastructure

Related items

• MediumEndor Labs’ AI SAST Finds Zero Day Memory-Amplification DoS in Anthropic’s buffa library | Endor LabsSimilar attack · Endor Labs Blog
• MediumCVE-2026-44627: Intel oneDNN integer overflow to buffer overflow in Ring 3 user applicationsSimilar attack · NVD/CVE Database
• MediumGHSA-h7c4-q426-7jh9: tsParticles: A single anonymous MCP session can monopolize HTTP mode and deny new clientsSimilar attack · GitHub Advisory Database
• HighGHSA-4p8p-pjpq-2w7h: tsParticles: Malformed JSON requests can terminate the @tsparticles/mcp-server HTTP processSimilar attack · GitHub Advisory Database
• HighGHSA-447x-qqwf-m7xq: tsParticles: Unbounded HTTP Request Body Buffering in @tsparticles/mcp-server Leads to Remote DoSSimilar attack · GitHub Advisory Database