CVE-2026-94627

概要

参考情報

• vllm-project/vllm · Product
• vllm-project/vllm · Product
• vllm-project/vllm#49796 · Issue Tracking
• vulncheck.com/advisories/vllm-through-0.29.0-gpu-kv-cache-leak-via-mooncake-transfer-id-collision · Third Party Advisory

vllm のその他の脆弱性

• CVE-2026-115918中 6.5vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authentica…
• CVE-2026-115917中 4.7vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMi…
• CVE-2026-115916中 6.5vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-…
• CVE-2026-115915緊急 9.8vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attacker-controlled image bytes to P…
• CVE-2026-115914中 6.5vLLM is an inference and serving engine for large language models. From 0.11.1 until 0.32.0, the DeepSeek-OCR, DeepSeek-OCR-2, and Unlimited…