Toolchain · 2023
vLLM
LLM inference and serving engine, started at UC Berkeley (PagedAttention paper, 2023).
What is vLLM written in?
Its runtime is implemented in Python, CUDA, PyTorch, and Triton (documented).
Frequently Asked Questions
What language is vLLM written in?
vLLM is primarily implemented in Python and CUDA and PyTorch and Triton.
When was vLLM first released?
vLLM was first released in 2023.
Evidence Sources
- https://github.com/vllm-project/vllm/tree/main/vllm Source repository
- https://github.com/vllm-project/vllm/tree/main/csrc Source repository
- https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/models/llama.py Source repository
- https://github.com/vllm-project/vllm/tree/main/vllm/v1/attention/ops Source repository
Discover More
Spot something wrong?
Every fact on this page is meant to be checkable. If one is wrong, say so and it becomes a dataset change, not a patch to this page.