1481 matches found
vLLM 代码问题漏洞
vLLM is an open-source solution designed for LLM-based models, featuring high throughput and memory-efficient reasoning and service engines. Versions of vLLM prior to 0.16.0 to 0.19.0 contained code vulnerabilities. These vulnerabilities stemmed from a lack of URL validation in the...
CVE-2026-34756: Allocation of Resources Without Limits or Throttling
vLLM is an inference and serving engine for large language models LLMs. From 0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionReques...
CVE-2026-34755: Allocation of Resources Without Limits or Throttling
vLLM is an inference and serving engine for large language models LLMs. From 0.7.0 to before 0.19.0, the VideoMediaIO.loadbase64 method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The numframes...
Server-side Request Forgery (SSRF)
Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the downloadbytesfromurl function. An attacker can cause the server to make arbitrary HTTP or HTTPS requests to...
GHSA-3MWP-WVH9-7528 vLLM: Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server
Summary A Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionRequest Pydantic models, an unauthenticated attacker can send a single HTTP request with an...
vLLM: Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server
Summary A Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionRequest Pydantic models, an unauthenticated attacker can send a single HTTP request with an...
Allocation of Resources Without Limits or Throttling
Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling due to the lack of upper bound validation on the n parameter in the request handling process. A...
PT-2026-30199
Name of the Vulnerable Software and Affected Versions vLLM versions 0.1.0 through 0.18.9 Description A Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionReques...
Improper Input Validation
Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Improper Input Validation due to inconsistent downmixing behavior in the tomono process. An attacker can manipulate audio inputs to cause the AI mod...
CVE-2026-34760
vLLM is an inference and serving engine for large language models LLMs. From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing tomono, while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results...
PYSEC-2026-2299
vLLM is an inference and serving engine for large language models LLMs. From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing tomono, while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results...
CVE-2026-34760 vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models
vLLM is an inference and serving engine for large language models LLMs. From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing tomono, while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results...
CVE-2026-34760
vLLM is an inference and serving engine for large language models LLMs. From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing tomono, while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results...
CVE-2026-34760: Improper Input Validation
vLLM is an inference and serving engine for large language models LLMs. From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing tomono, while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results...
GHSA-7972-PG2X-XR59 vulnerabilities
Vulnerabilities for packages: tritonserver-backend-vllm-cuda-13.0, vllm-openai-cuda-12.9, py3-vllm-cuda-12.4...
CVE-2026-27893 vulnerabilities
Vulnerabilities for packages: tritonserver-backend-vllm-cuda-13.0, vllm-openai-cuda-12.9, py3-vllm-cuda-12.4...
vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out
Summary Two model implementation files hardcode trustremotecode=True when loading sub-components, bypassing the user's explicit --trust-remote-code=False security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code...
GHSA-7972-PG2X-XR59 vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out
Summary Two model implementation files hardcode trustremotecode=True when loading sub-components, bypassing the user's explicit --trust-remote-code=False security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code...
Unsafe Dependency Resolution
Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Unsafe Dependency Resolution in the process of loading sub-components with the trustremotecode parameter set to True, regardless of user...