mirror of
https://github.com/bentoml/OpenLLM.git
synced 2025-12-23 23:57:46 -05:00
3f048d8a5b
* chore(qol): update CLI options and performance upgrade for build cache Signed-off-by: paperspace <29749331+aarnphm@users.noreply.github.com> * chore: update default python version for dev Signed-off-by: paperspace <29749331+aarnphm@users.noreply.github.com> * fix: install custom tar.gz models Signed-off-by: paperspace <29749331+aarnphm@users.noreply.github.com> --------- Signed-off-by: paperspace <29749331+aarnphm@users.noreply.github.com>
208 lines
6.3 KiB
TOML
208 lines
6.3 KiB
TOML
# NOTE: PEP517 is manged via ./tools/dependencies.py
|
|
[build-system]
|
|
build-backend = "hatchling.build"
|
|
requires = [
|
|
"hatchling==1.18.0",
|
|
"hatch-vcs==0.3.0",
|
|
"hatch-fancy-pypi-readme==23.1.0",
|
|
]
|
|
|
|
[project]
|
|
authors = [
|
|
{ name = "Aaron Pham", email = "aarnphm@bentoml.com" },
|
|
{ name = "BentoML Team", email = "contact@bentoml.com" },
|
|
]
|
|
classifiers = [
|
|
"Development Status :: 5 - Production/Stable",
|
|
"Environment :: GPU :: NVIDIA CUDA",
|
|
"Environment :: GPU :: NVIDIA CUDA :: 12",
|
|
"Environment :: GPU :: NVIDIA CUDA :: 11.8",
|
|
"Environment :: GPU :: NVIDIA CUDA :: 11.7",
|
|
"License :: OSI Approved :: Apache Software License",
|
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
"Topic :: Software Development :: Libraries",
|
|
"Operating System :: OS Independent",
|
|
"Intended Audience :: Developers",
|
|
"Intended Audience :: Science/Research",
|
|
"Intended Audience :: System Administrators",
|
|
"Typing :: Typed",
|
|
"Programming Language :: Python",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3 :: Only",
|
|
"Programming Language :: Python :: 3.8",
|
|
"Programming Language :: Python :: 3.9",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Programming Language :: Python :: Implementation :: CPython",
|
|
"Programming Language :: Python :: Implementation :: PyPy",
|
|
]
|
|
dependencies = [
|
|
"bentoml[io]>=1.2.16",
|
|
"transformers[torch,tokenizers]>=4.36.0",
|
|
"openllm-client>=0.5.0-alpha.14",
|
|
"openllm-core>=0.5.0-alpha.14",
|
|
"safetensors",
|
|
"vllm>=0.4.2",
|
|
"optimum>=1.12.0",
|
|
"accelerate",
|
|
"ghapi",
|
|
"einops",
|
|
"sentencepiece",
|
|
"scipy",
|
|
"build[virtualenv]<1",
|
|
"click>=8.1.3",
|
|
"cuda-python;platform_system!=\"Darwin\"",
|
|
"bitsandbytes<0.42",
|
|
]
|
|
description = "OpenLLM: Run any open-source LLMs, such as Llama 2, Mistral, as OpenAI compatible API endpoint in the cloud."
|
|
dynamic = ["version", "readme"]
|
|
keywords = [
|
|
"MLOps",
|
|
"AI",
|
|
"BentoML",
|
|
"Model Serving",
|
|
"Model Deployment",
|
|
"LLMOps",
|
|
"Falcon",
|
|
"Vicuna",
|
|
"Llama 2",
|
|
"Fine tuning",
|
|
"Serverless",
|
|
"Large Language Model",
|
|
"Generative AI",
|
|
"StableLM",
|
|
"Alpaca",
|
|
"PyTorch",
|
|
"Mistral",
|
|
"vLLM",
|
|
"Transformers",
|
|
]
|
|
license = "Apache-2.0"
|
|
name = "openllm"
|
|
requires-python = ">=3.8"
|
|
[project.scripts]
|
|
openllm = "_openllm_tiny._entrypoint:cli"
|
|
|
|
[project.urls]
|
|
Blog = "https://modelserving.com"
|
|
Chat = "https://discord.gg/openllm"
|
|
Documentation = "https://github.com/bentoml/openllm#readme"
|
|
GitHub = "https://github.com/bentoml/OpenLLM"
|
|
History = "https://github.com/bentoml/OpenLLM/blob/main/CHANGELOG.md"
|
|
Homepage = "https://bentoml.com"
|
|
Tracker = "https://github.com/bentoml/OpenLLM/issues"
|
|
Twitter = "https://twitter.com/bentomlai"
|
|
|
|
[project.optional-dependencies]
|
|
agents = ["transformers[agents]>=4.36.0", "diffusers", "soundfile"]
|
|
all = ["openllm[full]"]
|
|
awq = ["autoawq"]
|
|
baichuan = ["cpm-kernels"]
|
|
chatglm = ["cpm-kernels"]
|
|
dbrx = ["cpm-kernels"]
|
|
dolly-v2 = ["cpm-kernels"]
|
|
falcon = ["xformers"]
|
|
fine-tune = ["peft>=0.6.0", "datasets", "trl", "huggingface-hub"]
|
|
flan-t5 = ["xformers"]
|
|
full = [
|
|
"openllm[agents,awq,baichuan,chatglm,dbrx,dolly-v2,falcon,fine-tune,flan-t5,gemma,ggml,gpt-neox,gptq,grpc,llama,mistral,mixtral,mpt,openai,opt,phi,playground,qwen,stablelm,starcoder,vllm,yi]",
|
|
]
|
|
gemma = ["xformers"]
|
|
ggml = ["ctransformers"]
|
|
gpt-neox = ["xformers"]
|
|
gptq = ["auto-gptq[triton]>=0.4.2"]
|
|
grpc = ["bentoml[grpc]>=1.2.16"]
|
|
llama = ["xformers"]
|
|
mistral = ["xformers"]
|
|
mixtral = ["xformers"]
|
|
mpt = ["triton"]
|
|
openai = ["openai[datalib]>=1", "tiktoken", "fastapi"]
|
|
opt = ["triton"]
|
|
phi = ["triton"]
|
|
playground = ["jupyter", "notebook", "ipython", "jupytext", "nbformat"]
|
|
qwen = ["cpm-kernels", "tiktoken"]
|
|
stablelm = ["cpm-kernels", "tiktoken"]
|
|
starcoder = ["bitsandbytes"]
|
|
vllm = ["vllm==0.4.2"]
|
|
yi = ["bitsandbytes"]
|
|
|
|
[tool.hatch.version]
|
|
fallback-version = "0.0.0"
|
|
source = "vcs"
|
|
[tool.hatch.build.hooks.vcs]
|
|
version-file = "src/openllm/_version.py"
|
|
[tool.hatch.version.raw-options]
|
|
git_describe_command = [
|
|
"git",
|
|
"describe",
|
|
"--dirty",
|
|
"--tags",
|
|
"--long",
|
|
"--first-parent",
|
|
]
|
|
local_scheme = "no-local-version"
|
|
root = ".."
|
|
[tool.hatch.metadata]
|
|
allow-direct-references = true
|
|
[tool.hatch.build.targets.wheel]
|
|
only-include = ["src/openllm", "src/openllm_cli", "src/_openllm_tiny"]
|
|
sources = ["src"]
|
|
[tool.hatch.build.targets.sdist]
|
|
exclude = ["/.git_archival.txt", "tests", "/.python-version-default"]
|
|
[tool.hatch.metadata.hooks.fancy-pypi-readme]
|
|
content-type = "text/markdown"
|
|
# PyPI doesn't support the <picture> tag.
|
|
[[tool.hatch.metadata.hooks.fancy-pypi-readme.fragments]]
|
|
text = """
|
|
<p align="center">
|
|
<a href="https://github.com/bentoml/openllm">
|
|
<img src="https://raw.githubusercontent.com/bentoml/openllm/main/.github/assets/main-banner.png" alt="Banner for OpenLLM" />
|
|
</a>
|
|
</p>
|
|
|
|
"""
|
|
[[tool.hatch.metadata.hooks.fancy-pypi-readme.fragments]]
|
|
end-before = "\n<!-- hatch-fancy-pypi-readme intro stop -->"
|
|
path = "README.md"
|
|
start-after = "<!-- hatch-fancy-pypi-readme intro start -->\n"
|
|
[[tool.hatch.metadata.hooks.fancy-pypi-readme.fragments]]
|
|
text = """
|
|
|
|
<p align="center">
|
|
<img src="https://raw.githubusercontent.com/bentoml/openllm/main/.github/assets/output.gif" alt="Gif showing OpenLLM Intro" />
|
|
</p>
|
|
"""
|
|
[[tool.hatch.metadata.hooks.fancy-pypi-readme.fragments]]
|
|
end-before = "\n<!-- hatch-fancy-pypi-readme interim stop -->"
|
|
path = "README.md"
|
|
start-after = "<!-- hatch-fancy-pypi-readme interim start -->\n"
|
|
[[tool.hatch.metadata.hooks.fancy-pypi-readme.fragments]]
|
|
text = """
|
|
|
|
<p align="center">
|
|
<img src="https://raw.githubusercontent.com/bentoml/openllm/main/.github/assets/agent.gif" alt="Gif showing Agent integration" />
|
|
</p>
|
|
"""
|
|
[[tool.hatch.metadata.hooks.fancy-pypi-readme.fragments]]
|
|
end-before = "\n<!-- hatch-fancy-pypi-readme meta stop -->"
|
|
path = "README.md"
|
|
start-after = "<!-- hatch-fancy-pypi-readme meta start -->\n"
|
|
[[tool.hatch.metadata.hooks.fancy-pypi-readme.fragments]]
|
|
text = """
|
|
|
|
## Release Information
|
|
|
|
"""
|
|
[[tool.hatch.metadata.hooks.fancy-pypi-readme.fragments]]
|
|
path = "CHANGELOG.md"
|
|
pattern = "\n(###.+?\n)## "
|
|
start-after = "<!-- towncrier release notes start -->"
|
|
[[tool.hatch.metadata.hooks.fancy-pypi-readme.fragments]]
|
|
text = """
|
|
|
|
---
|
|
|
|
[Click me for full changelog](https://github.com/bentoml/openllm/blob/main/CHANGELOG.md)
|
|
"""
|