CVE-2026-44223

01/תיאור (מקור, אנגלית)

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 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.

02/מוצרים מושפעים

vllm: vllm

03/קישורים4

• github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52‮… MitigationVendor Advisory
• github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52‮… MitigationVendor Advisory
• github.com/vllm-project/vllm/pull/38610 Issue TrackingPatch
• github.com/vllm-project/vllm/pull/38610 Issue TrackingPatch