Soup/pyproject.toml at v0.72.3 · ghzhost/Soup · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[project]
name = "soup-cli"
version = "0.72.3"
description = "Fine-tune and post-train LLMs in one command. No SSH, no config hell."
readme = "README.md"
license = "Apache-2.0"
requires-python = ">=3.10"
authors = [
    { name = "Soup Team" },
]
keywords = ["llm", "fine-tuning", "lora", "qlora", "machine-learning"]
classifiers = [
    "Development Status :: 3 - Alpha",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "License :: OSI Approved :: Apache Software License",
    "Programming Language :: Python :: 3",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
]
# Core install (`pip install soup-cli`) is intentionally light: the CLI, config
# system, and data tools вЂ” no PyTorch. v0.71.0 split the heavy training stack
# (torch / transformers / peft / trl / datasets / bitsandbytes / accelerate)
# into the `[train]` extra below.
dependencies = [
    "typer>=0.9.0,<0.21.0",
    "rich>=13.0.0",
    "pydantic>=2.0.0",
    "pyyaml>=6.0",
    "huggingface-hub>=0.16.0",
    "plotext>=5.2.0",
]

[project.optional-dependencies]
# v0.71.0 вЂ” heavy training stack. `pip install 'soup-cli[train]'` to fine-tune.
# These were core dependencies through v0.70.0; pins are unchanged.
train = [
    "torch>=2.0.0",
    "transformers>=4.36.0,<5.0.0",
    "peft>=0.7.0",
    "trl>=0.7.0",
    "datasets>=2.14.0",
    "bitsandbytes>=0.41.0",
    "accelerate>=0.25.0",
]
# v0.71.0 вЂ” convenience meta-extra pulling the main optional stacks.
all = ["soup-cli[train,serve,ui,data,mcp]"]
eval = ["lm-eval>=0.4.0"]
data = ["datasketch>=1.6.0"]
wandb = ["wandb>=0.15.0,<0.18.0"]
# Self-references `[train]` so CI / contributors get the full training stack
# (CI runs `pip install -e ".[dev]"`; without this every test would fail at
# `import torch`).
dev = ["soup-cli[train,mcp]", "cryptography>=41.0.0", "reportlab>=4.0.0", "pytest>=7.0", "ruff>=0.1.0", "pytest-cov>=4.0", "httpx>=0.24.0", "mypy>=1.8.0", "pre-commit>=3.5.0"]
ui = ["fastapi>=0.104.0", "uvicorn>=0.24.0"]
serve = ["fastapi>=0.104.0", "uvicorn>=0.24.0"]
serve-fast = ["vllm>=0.4.0", "fastapi>=0.104.0", "uvicorn>=0.24.0"]
generate = ["httpx>=0.24.0"]
deepspeed = ["deepspeed>=0.12.0"]
fast = ["unsloth>=2024.8"]
vision = ["Pillow>=9.0.0"]
qat = ["torchao>=0.4.0"]
liger = ["liger-kernel>=0.3.0"]
ring-attn = ["ring-flash-attn>=0.1.0"]
onnx = ["optimum[onnxruntime]>=1.16.0"]
tensorrt = ["tensorrt_llm>=0.9.0"]
audio = ["librosa>=0.10.0", "soundfile>=0.12.0"]
awq = ["autoawq>=0.2.0"]
gptq = ["auto-gptq>=0.7.0"]
sglang = ["sglang>=0.2.0", "fastapi>=0.104.0", "uvicorn>=0.24.0"]
mlx = ["mlx>=0.20.0", "mlx-lm>=0.20.0"]
cce = ["cut-cross-entropy>=24.10.0"]
tui = ["textual>=0.50.0"]
# v0.53.8 #89 вЂ” bundle MLflow / SwanLab / Trackio for `--tracker` users.
trackers = ["mlflow>=2.0.0", "swanlab>=0.3.0", "trackio>=0.0.1"]
# v0.53.8 #85 вЂ” fsspec backends for remote dataset loading (s3 / gs / az / oci).
remote = ["fsspec>=2024.1.0", "s3fs>=2024.1.0", "gcsfs>=2024.1.0", "adlfs>=2024.1.0"]
# v0.53.10 #150 вЂ” bundle scikit-optimize so `soup data mix --optimize` runs the
# Bayesian-style loop instead of falling back to the v0.48.0 Dirichlet sampler.
mix = ["scikit-optimize>=0.9.0"]
# v0.53.10 #113 вЂ” production-grade data quality: langdetect (language) +
# presidio-analyzer (PII). Llama-Guard-3-1B is documented as a manual recipe
# (license + ~600 MB weight blob too large to bundle by default).
data-pro = ["langdetect>=1.0.9", "presidio-analyzer>=2.2.0"]
# v0.71.2 #179/#185 вЂ” ed25519 detached signing for `soup attest` / `soup
# adapters sign`. Pure-offline; Sigstore keyless (OIDC + Fulcio/Rekor network)
# stays infra-blocked and is NOT bundled here.
sign = ["cryptography>=41.0.0"]
# v0.71.3 #181 вЂ” reportlab PDF rendering for `soup train --annex-xi *.pdf`.
pdf = ["reportlab>=4.0.0"]
# v0.71.3 #180 вЂ” codecarbon offline energy/CO2 measurement for
# `soup train --track-energy` (offline; no IP-geolocation network call).
carbon = ["codecarbon>=2.0.0"]
# v0.71.13 #225/#227 вЂ” prompt-program / tool-schema compilers
# (`soup compile` / `soup compile-tools`). Lazy-imported with a friendly
# ImportError; not installed by default (heavy dependency trees).
compile = ["dspy-ai>=2.5.0", "textgrad>=0.1.0", "gepa>=0.0.1"]
# v0.71.18 #16 вЂ” serverless cloud GPU training (`soup train --cloud modal`).
# Lazy-imported; only needed for `--cloud-submit` (plan-only render needs no
# dependency). Modal auth is via `modal setup`.
modal = ["modal>=0.60.0"]
# v0.71.28 - `soup mcp serve` MCP server. The official `mcp` python SDK is
# lazy-imported (only src/soup_cli/mcp_server/server.py touches it), so the CLI
# stays light without it. Floor pinned to guard against SDK API churn.
#
# v0.72.3: capped below 2.0. The floor alone was not enough — mcp 2.0.0 removed
# `mcp.shared.memory.create_connected_server_and_client_session` and dropped
# `Server.list_tools`, which broke every `soup mcp serve` round-trip test on all
# nine CI jobs the day it was published. 1.29.0 (the newest 1.x) still exposes
# both, verified directly. Migrating to the 2.x API is its own piece of work,
# and shipping against a major nobody has validated is not a substitute for it.
mcp = ["mcp>=1.2.0,<2"]

[project.scripts]
soup = "soup_cli.cli:run"

[project.urls]
Homepage = "https://github.com/MakazhanAlpamys/Soup"
Repository = "https://github.com/MakazhanAlpamys/Soup"
Issues = "https://github.com/MakazhanAlpamys/Soup/issues"

[tool.hatch.build.targets.wheel]
packages = ["src/soup_cli"]
# v0.53.8 #93 вЂ” include bundled fixture JSONLs as package data so
# `soup data demo` works in zipapp / namespace-package installs.
# Hatchling's ``packages = ["src/soup_cli"]`` already recurses into the
# package directory, so we use the artifacts directive (NOT
# force-include, which double-shipped the files in v0.53.8 and produced
# a "duplicate filename in local headers" 400 from PyPI upload).
artifacts = [
  "src/soup_cli/data/_fixtures/*.jsonl",
  "src/soup_cli/data/_fixtures/unlearning/*.jsonl",
  "src/soup_cli/data/_fixtures/behavior/*.jsonl",
  "src/soup_cli/data/_fixtures/gate/*.jsonl",
]

[tool.ruff]
target-version = "py310"
line-length = 100

[tool.ruff.lint]
select = ["E", "F", "I", "N", "W"]

[tool.mypy]
# Intentionally lenient: the codebase leans on torch / transformers / peft / trl,
# none of which ship complete stubs. This config surfaces type issues in our own
# code without drowning in third-party `Any`s. The CI `type-check` job is
# non-blocking; tighten incrementally as modules gain annotations.
python_version = "3.10"
files = ["src/soup_cli"]
ignore_missing_imports = true
follow_imports = "silent"

[tool.pytest.ini_options]
testpaths = ["tests"]
markers = [
    "smoke: slow smoke tests that download models and run training (run with: pytest -m smoke)",
    "unit: fast isolated tests вЂ” no subprocess, network, filesystem, or real model load",
    "integration: tests that touch real subprocess, SQLite, filesystem, or HTTP",
]
addopts = "-m 'not smoke' --cov=soup_cli --cov-fail-under=77 --cov-report=term-missing:skip-covered"