130 results · Feed
-
Low 2.6
vLLM’s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel
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 PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time…
-
Critical 9.8
vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
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 using the `PyNcclPipe` KV cache transfer integration with the V0 engine. No other configurations are affected. …
-
High 8.0
Remote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration
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 multi-node communication purposes. The secondary vLLM hosts open a `SUB` ZeroMQ socket and connect to an `XPUB` s…
-
Critical 10.0
vLLM Vulnerable to Remote Code Execution via Mooncake Integration
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 integration with mooncake, are vulnerable to remote code execution due to using pickle based serialization over …
-
Medium 6.5
vLLM phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service
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 by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code d…
-
High 7.5
Data exposure via ZeroMQ on multi-node vLLM deployment
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 vulnerable to denial of service and data exposure via ZeroMQ on multi-node vLLM deployment. In a multi-node vLLM deployme…
-
Critical 9.1
vLLM Allows Remote Code Execution via Mooncake Integration
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 distri…
-
Medium 6.5
vLLM denial of service via outlines unbounded cache on disk
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…
-
Low 2.6
vLLM using built-in hash() from Python 3.12 leads to predictable hash collisions in vLLM prefix cache
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…
-
High 7.5
vLLM allows a malicious model RCE by torch.load in hf_model_weights_iterator
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 defaul…