PyPI package
vllm
pkg:pypi/vllm
Vulnerabilities (47)
| CVE | Sev | CVSS | KEV | Affected versions | Fixed in | Published | Description |
|---|---|---|---|---|---|---|---|
| CVE-2024-11041 | Cri | 9.8 | <= 0.6.2 | — | Mar 20, 2025 | vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses pickle.loads to parse received sockets directly, leading to a remote code execution vulnerability. An attacker can exploit this by sending a malicious payload t | |
| CVE-2025-29783 | Cri | 9.0 | >= 0.6.5, < 0.8.0 | 0.8.0 | Mar 19, 2025 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is | |
| CVE-2025-29770 | Med | 6.5 | < 0.8.0 | 0.8.0 | Mar 19, 2025 | 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 support structured output (a.k.a. guided decoding). Outlines provides an optional cache for its compiled grammars on the local filesys | |
| CVE-2025-25183 | Low | 2.6 | < 0.7.2 | 0.7.2 | Feb 7, 2025 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of | |
| CVE-2025-24357 | Hig | 7.5 | < 0.7.0 | 0.7.0 | Jan 27, 2025 | vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It uses the torch.load function and the weights_only parameter defaults to False. When tor | |
| CVE-2024-8939 | Med | 6.2 | <= 0.5.0.post1 | — | Sep 17, 2024 | A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best comp | |
| CVE-2024-8768 | Hig | 7.5 | < 0.5.5 | 0.5.5 | Sep 17, 2024 | A flaw was found in the vLLM library. A completions API request with an empty prompt will crash the vLLM API server, resulting in a denial of service. |
- affected <= 0.6.2
vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses pickle.loads to parse received sockets directly, leading to a remote code execution vulnerability. An attacker can exploit this by sending a malicious payload t
- affected >= 0.6.5, < 0.8.0fixed 0.8.0
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is
- affected < 0.8.0fixed 0.8.0
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 support structured output (a.k.a. guided decoding). Outlines provides an optional cache for its compiled grammars on the local filesys
- affected < 0.7.2fixed 0.7.2
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of
- affected < 0.7.0fixed 0.7.0
vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It uses the torch.load function and the weights_only parameter defaults to False. When tor
- affected <= 0.5.0.post1
A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best comp
- affected < 0.5.5fixed 0.5.5
A flaw was found in the vLLM library. A completions API request with an empty prompt will crash the vLLM API server, resulting in a denial of service.
Page 3 of 3