Package profile
vllm
- Summary: A high-throughput and memory-efficient inference and serving engine for LLMs
- Author: vLLM Team
- License: Apache-2.0
- Homepage: https://github.com/vllm-project/vllm
- Documentation: https://docs.vllm.ai/en/latest/
- Source: https://github.com/vllm-project/vllm
- Number of releases: 99
- First release: 0.0.1 on 2023-06-19
- Latest release: 0.31.0 on 2026-10-05
- Latest release size: 295.7 MB (wheel)
93 known vulnerabilitiesLatest: GHSA-ph3r-5jfg-f84f — vLLM: Mirrored multimodal IPC caches desync after a rejected request — a later request reusing the same media hash trips a receiver assertion in the engine core View all →
Dependencies
Vllm has 92 dependencies, 17 of which optional.Dependent packages
| Package | Optional | Group |
|---|---|---|
| rank-llm | false | |
| vllm-gguf-plugin | false | |
| agno | true | vllm |
| apache-beam | true | vllm |
| evalplus | true | vllm |
Similar packages
- instructorstructured outputs for llm
- genai-pricesCalculate prices for calling LLM inference APIs.
- llama-indexInterface between LLMs and your data
- llama-index-coreInterface between LLMs and your data
- llama-index-legacyInterface between LLMs and your data
- deepevalThe LLM Evaluation Framework
- langgraphBuilding stateful, multi-actor applications with LLMs