pyproject.toml

[tool.poetry]
name = "text-generation-server"
version = "1.0.1"
description = "Text Generation Inference Python gRPC Server"
authors = ["Olivier Dehaene <olivier@huggingface.co>"]

[tool.poetry.scripts]
text-generation-server = 'text_generation_server.cli:app'

[tool.poetry.dependencies]
python = ">=3.9,<3.13"
protobuf = "^4.21.7"
grpcio = "^1.51.1"
grpcio-status = "^1.51.1"
grpcio-reflection = "^1.51.1"
grpc-interceptor = "^0.15.0"
typer = "^0.6.1"
accelerate = { version = "^0.20.0", optional = true }
bitsandbytes = { version = "^0.41.1", optional = true }
safetensors = "^0.3.2"
loguru = "^0.6.0"
opentelemetry-api = "^1.15.0"
opentelemetry-exporter-otlp = "^1.15.0"
opentelemetry-instrumentation-grpc = "^0.36b0"
hf-transfer = "^0.1.2"
sentencepiece = "^0.1.97"
tokenizers = "^0.13.3"
huggingface-hub = "^0.14.1"
transformers = "^4.31.0"
einops = "^0.6.1"
texttable = { version = "^1.6.7", optional = true }
datasets = { version = "^2.14.0", optional = true }
peft = "^0.4.0"
torch = {version = "^2.0.1+cu118", source = "pytorch-gpu-src"}
scipy = "^1.11.1"

[tool.poetry.extras]
accelerate = ["accelerate"]
bnb = ["bitsandbytes"]
quantize = ["texttable", "datasets", "accelerate"]

[tool.poetry.group.dev.dependencies]
grpcio-tools = "^1.51.1"
pytest = "^7.3.0"


[[tool.poetry.source]]
name = "pytorch-gpu-src"
url = "https://download.pytorch.org/whl/cu118"
priority = "explicit"

[tool.pytest.ini_options]
markers = ["private: marks tests as requiring an admin hf token (deselect with '-m \"not private\"')"]

[build-system]
requires = ["poetry-core>=1.0.0"]
build-backend = "poetry.core.masonry.api"