CONTENTUM.COMA specialist. A plan. A result.

Vulnerabilities · Vendors

Vllm
25 vulnerabilities.

All published vulnerabilities with a CVE number in Vllm products, newest first, with severity and references.

CVESummaryPublishedCVSS
CVE-2026-24779Vllm: vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.14.1, a Server-Side Request Forgery (SSRF) …2026-01-277.1
CVE-2026-22807Vllm: vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads …2026-01-218.8
CVE-2026-22773Vllm: vLLM is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine …2026-01-106.5
CVE-2025-66448Vllm: vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a …2025-12-017.1
CVE-2025-62426Vllm: vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and …2025-11-216.5
CVE-2025-62372Vllm: vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine …2025-11-216.5
CVE-2025-62164Vllm: vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability …2025-11-218.8
CVE-2025-59425Vllm: vLLM is an inference and serving engine for large language models (LLMs). Before version 0.11.0rc2, the API key support in vLLM performs validation …2025-10-077.5
CVE-2025-48956Vllm: vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability …2025-08-217.5
CVE-2025-48944Vllm: vLLM is an inference and serving engine for large language models (LLMs). In version 0.8.0 up to but excluding 0.9.0, the vLLM backend used with …2025-05-306.5
CVE-2025-48943Vllm: vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service (ReDoS) …2025-05-306.5
CVE-2025-48942Vllm: vLLM is an inference and serving engine for large language models (LLMs). In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions …2025-05-306.5
CVE-2025-48887Vllm: vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the …2025-05-306.5
CVE-2025-47277Vllm: vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments …2025-05-209.8
CVE-2025-46722Vllm: vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file …2025-05-294.2
CVE-2025-46570Vllm: vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the …2025-05-292.6
CVE-2025-46560Vllm: vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected …2025-04-296.5
CVE-2025-32444Vllm: vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM …2025-04-2910.0
CVE-2025-30202Vllm: vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.5.2 and prior to 0.8.5 are …2025-04-297.5
CVE-2025-30165Vllm: vLLM is an inference and serving engine for large language models. In a multi-node vLLM deployment using the V0 engine, vLLM uses ZeroMQ for some …2025-05-068.0
CVE-2025-29783Vllm: vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe …2025-03-199.0
CVE-2025-29770Vllm: vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. The outlines library is one of the backends used by vLLM to …2025-03-196.5
CVE-2025-25183Vllm: vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash …2025-02-072.6
CVE-2025-24357Vllm: vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model …2025-01-277.5
CVE-2024-11041Vllm: vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses pickle.loads to parse …2025-03-209.8

Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.

Too many to
patch at once?

Providers for vulnerability management find the affected systems in your environment, set the order and keep the patching going.