vLLM是vLLM团队开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.27.0之前版本存在数字错误漏洞,该漏洞源于activation_kernels.cu中blockIdx.x 2 d存在整数溢出,可能导致同一推理批次中其他请求获取另一个用户的部分或全部推理结果。
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| vllm-project | vllm | < 0.27.0 |
affected |
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| vllm-project | vllm | < 0.27.0 | - |
|
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POC| CVE-2026-73559 | 6.5 MEDIUM | vLLM: Completion prompt lists fan out into unbounded engine requests |
| CVE-2026-73557 | 6.3 MEDIUM | vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts |
| CVE-2026-73555 | 5.3 MEDIUM | vLLM: Unauthenticated Internal Path and Username Disclosure via Validation Error Messages |
| CVE-2026-73556 | 5.3 MEDIUM | vLLM: ReDoS via structured_outputs.regex in the lm-format-enforcer backend (no compile tim |
No comments yet