vLLM is an inference and serving engine for large language models (LLMs). From to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., "repetition_penalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.
beschreibt (1)
Zugehörige CVEs.
| ID | Schweregrad | ausnutzbar | ||
|---|---|---|---|---|
| CVE-2026-44223US | — | — | ||
vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a te… | ||||
Referenzen
Externe Belege — Patches, Meldungen, Analysen.
Advisories wie diese benennen die exponierten Produkte, die Angreifer auf Ihrer Angriffsfläche ins Visier nehmen. Sehen Sie mit einem kostenlosen Passiv-Scan, was exponiert ist.
Kostenloser Scan