vllm/requirements-neuron.txt

sentencepiece  # Required for LLaMA tokenizer.
numpy
transformers-neuronx >= 0.9.0
torch-neuronx >= 2.1.0
neuronx-cc
fastapi
uvicorn[standard]
pydantic >= 2.0  # Required for OpenAI server.
prometheus_client >= 0.18.0
[Neuron] Add an option to build with neuron (#2065) 2024-01-19 02:58:50 +08:00			`sentencepiece # Required for LLaMA tokenizer.`
			`numpy`
			`transformers-neuronx >= 0.9.0`
			`torch-neuronx >= 2.1.0`
			`neuronx-cc`
			`fastapi`
			`uvicorn[standard]`
migrate pydantic from v1 to v2 (#2531) 2024-01-22 08:05:56 +08:00			`pydantic >= 2.0 # Required for OpenAI server.`
Restrict prometheus_client >= 0.18.0 to prevent errors when importing pkgs (#3070) 2024-02-28 13:38:26 +08:00			`prometheus_client >= 0.18.0`