747 matches found
vLLM 安全漏洞
vLLM is a high throughput and memory efficient inference and service engine for LLM from the vLLM open source. A security vulnerability exists in vLLM versions prior to 0.8.0 through 0.8.5, which stems from inefficiencies in the input preprocessing logic that could lead to resource exhaustion...
vLLM Vulnerable to Remote Code Execution via Mooncake Integration
Impacted Deployments Note that vLLM instances that do NOT make use of the mooncake integration are NOT vulnerable. Description vLLM integration with mooncake is vaulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerable sockets were...
Data exposure via ZeroMQ on multi-node vLLM deployment
Impact In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-node communication purposes. The primary vLLM host opens an XPUB ZeroMQ socket and binds it to ALL interfaces. While the socket is always opened for a multi-node deployment, it is only used when doing tensor parallelism acros...
PT-2025-18215
Name of the Vulnerable Software and Affected Versions vLLM versions 0.5.2 through 0.8.5 Description The issue affects vLLM, a high-throughput and memory-efficient inference and serving engine for LLMs. In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-node communication purposes,...
Denial Of Service (DoS)
vllm is vulnerable to Denial of Service DoS. The vulnerability is due to unbounded in-memory cache growth due to allowing unique schema requests to continually populate the grammar cache, potentially exhausting system RAM...
GHSA-GGPF-24JW-3FCW CVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0
Description https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54 reported a vulnerability where loading a malicious model could result in code execution on the vllm host. The fix applied to specify weightsonly=True to calls to torch.load did not solve the problem prior to...
vLLM vulnerable to Denial of Service by abusing xgrammar cache
Impact This report is to highlight a vulnerability in XGrammar, a library used by the structured output feature in vLLM. The XGrammar advisory is here: https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3 The xgrammar library is the default backend used by vLLM to support...
GHSA-HF3C-WXG2-49Q9 vLLM vulnerable to Denial of Service by abusing xgrammar cache
Impact This report is to highlight a vulnerability in XGrammar, a library used by the structured output feature in vLLM. The XGrammar advisory is here: https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3 The xgrammar library is the default backend used by vLLM to support...
CVE-2025-1979 vulnerabilities
Vulnerabilities for packages: py3.10-vllm-cuda-12.6...
GHSA-W4RH-FGX7-Q63M vulnerabilities
Vulnerabilities for packages: py3.10-vllm-cuda-12.6...
GHSA-389X-67PX-MJG3 vulnerabilities
Vulnerabilities for packages: py3.10-vllm-cuda-11.8...
CVE-2025-32381 vulnerabilities
Vulnerabilities for packages: py3.10-vllm-cuda-11.8...
PT-2025-22278
Name of the Vulnerable Software and Affected Versions vLLM versions 0.6.5 through 0.8.4 Description vLLM, an inference and serving engine for large language models LLMs, contains a remote code execution issue. This impacts environments utilizing the PyNcclPipe KV cache transfer integration with t...
CVE-2024-9052 vulnerabilities
Vulnerabilities for packages: py3.10-vllm-cuda-11.8...
GHSA-PGR7-MHP5-FGJP vulnerabilities
Vulnerabilities for packages: py3.10-vllm-cuda-11.8...
Remote Code Execution (RCE)
vllm is vulnerable to Remote Code Execution RCE. The vulnerability is due to unsafe deserialization exposed over ZMQ/TCP on all network interfaces when vLLM is configured to use Mooncake, allowing an attacker to execute arbitrary code on distributed hosts...
CVE-2024-9053
A flaw was found in the vLLM AsyncEngineRPCServer. This vulnerability allows remote code execution via deserialization of untrusted data. Mitigation Mitigation for this issue is either not available or the currently available options don't meet the Red Hat Product Security criteria comprising eas...
CVE-2024-9052
A flaw was found in the vLLM distributed training API. This vulnerability allows remote code execution via unsafe deserialization, which uses pickle.loads without sanitization...