mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-24 16:32:12 +00:00
cb747b33da
* Add fp8 support moe models add deepseekv3 format codfe' update dockerfile update doc * Small modifications. * Moe kernels 0.8.1 * Upgrade to 0.8.1 * Fixing moe import. * Black. * Apply suggestions from code review Co-authored-by: Mohit Sharma <mohit21sharma.ms@gmail.com> * Fixing Mixtral + Nits. * Put link to ref. * Fix other call locations. * Scoring func `softmax` is the only one that works. --------- Co-authored-by: Mohit Sharma <mohit21sharma.ms@gmail.com>
88 lines
2.8 KiB
TOML
88 lines
2.8 KiB
TOML
[project]
|
|
name = "text-generation-server"
|
|
version = "2.0.5-dev0"
|
|
description = "Text Generation Inference Python gRPC Server"
|
|
readme = "README.md"
|
|
requires-python = ">=3.9"
|
|
authors = [
|
|
{name = "Olivier Dehaene", email = "olivier@huggingface.co"},
|
|
{name = "Nicolas Patry", email = "nicolas@huggingface.co"},
|
|
]
|
|
dependencies = [
|
|
"einops>=0.8.0",
|
|
"grpc-interceptor>=0.15.4",
|
|
"grpcio>=1.67.0",
|
|
"grpcio-reflection>=1.67.0",
|
|
"grpcio-status>=1.67.0",
|
|
"hf-transfer>=0.1.8",
|
|
"loguru>=0.7.3",
|
|
"numpy>=1.26,<3",
|
|
"opentelemetry-api>=1.27.0",
|
|
"opentelemetry-exporter-otlp>=1.27.0",
|
|
"opentelemetry-instrumentation-grpc>=0.50b0",
|
|
"pillow>=11.1.0",
|
|
"prometheus-client>=0.21.0",
|
|
"protobuf>=5.28.3",
|
|
"py-cpuinfo>=9.0.0",
|
|
"rich>=13.8.1",
|
|
"safetensors>=0.4.5",
|
|
"scipy>=1.13.1",
|
|
"sentencepiece>=0.2.0",
|
|
"tokenizers>=0.20.3",
|
|
"typer>=0.15.1",
|
|
]
|
|
|
|
[project.scripts]
|
|
text-generation-server = "text_generation_server.cli:app"
|
|
|
|
[project.optional-dependencies]
|
|
accelerate = [
|
|
"accelerate>=1.2.1,<2",
|
|
]
|
|
bnb = [
|
|
"bitsandbytes>=0.45.0",
|
|
]
|
|
compressed-tensors = [
|
|
"compressed-tensors>=0.9.0",
|
|
]
|
|
peft = [
|
|
"peft>=0.14.0",
|
|
]
|
|
outlines = [
|
|
"outlines>=0.1.13",
|
|
]
|
|
dev = [
|
|
"grpcio-tools>=1.51.1,<2.0",
|
|
"pytest>=7.3.0,<8"
|
|
]
|
|
quantize = [
|
|
"texttable>=1.6.7,<2",
|
|
"datasets>=2.21,<3",
|
|
]
|
|
moe = [ "moe-kernels" ]
|
|
attention = [ "attention-kernels" ]
|
|
marlin = [ "marlin-kernels" ]
|
|
gen = [
|
|
"grpcio-tools>=1.69.0",
|
|
"mypy-protobuf>=3.6.0",
|
|
]
|
|
|
|
[tool.uv.sources]
|
|
attention-kernels.url = "https://github.com/danieldk/attention-kernels/releases/download/v0.2.0.post2/attention_kernels-0.2.0.post2+cu123torch2.5-cp39-abi3-linux_x86_64.whl"
|
|
marlin-kernels = [
|
|
{ url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp39-cp39-linux_x86_64.whl", marker = "python_version == '3.9'" },
|
|
{ url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp310-cp310-linux_x86_64.whl", marker = "python_version == '3.10'" },
|
|
{ url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp311-cp311-linux_x86_64.whl", marker = "python_version == '3.11'" },
|
|
{ url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp312-cp312-linux_x86_64.whl", marker = "python_version == '3.12'" },
|
|
]
|
|
moe-kernels.url = "https://github.com/danieldk/moe-kernels/releases/download/v0.8.1/moe_kernels-0.8.1+cu123torch2.5-cp39-abi3-linux_x86_64.whl"
|
|
|
|
[tool.pytest.ini_options]
|
|
markers = ["private: marks tests as requiring an admin hf token (deselect with '-m \"not private\"')"]
|
|
|
|
[tool.isort]
|
|
profile = "black"
|
|
|
|
[tool.setuptools.packages.find]
|
|
include = ["text_generation_server*"]
|