25 lines
695 B
Plaintext
25 lines
695 B
Plaintext
cmake >= 3.21
|
|
ninja # For faster builds.
|
|
psutil
|
|
sentencepiece # Required for LLaMA tokenizer.
|
|
numpy < 2.0.0
|
|
requests
|
|
tqdm
|
|
py-cpuinfo
|
|
transformers >= 4.42.0 # Required for Gemma 2 and for additional chat template parameters.
|
|
tokenizers >= 0.19.1 # Required for Llama 3.
|
|
fastapi
|
|
aiohttp
|
|
openai
|
|
uvicorn[standard]
|
|
pydantic >= 2.0 # Required for OpenAI server.
|
|
pillow # Required for image processing
|
|
prometheus_client >= 0.18.0
|
|
prometheus-fastapi-instrumentator >= 7.0.0
|
|
tiktoken >= 0.6.0 # Required for DBRX tokenizer
|
|
lm-format-enforcer == 0.10.1
|
|
outlines >= 0.0.43 # Requires torch >= 2.1.0
|
|
typing_extensions
|
|
filelock >= 3.10.4 # filelock starts to support `mode` argument from 3.10.4
|
|
pyzmq
|