2024-01-18 10:58:50 -08:00
|
|
|
sentencepiece # Required for LLaMA tokenizer.
|
|
|
|
numpy
|
|
|
|
transformers-neuronx >= 0.9.0
|
|
|
|
torch-neuronx >= 2.1.0
|
|
|
|
neuronx-cc
|
|
|
|
fastapi
|
|
|
|
uvicorn[standard]
|
2024-01-22 01:05:56 +01:00
|
|
|
pydantic >= 2.0 # Required for OpenAI server.
|
2024-02-28 13:38:26 +08:00
|
|
|
prometheus_client >= 0.18.0
|
2024-03-28 22:16:12 -07:00
|
|
|
requests
|
|
|
|
psutil
|
|
|
|
py-cpuinfo
|