Files
axolotl/pyproject.toml
NanoCode012 9de5b76336 feat: move to uv first (#3545)
* feat: move to uv first

* fix: update doc to uv first

* fix: merge dev/tests into uv pyproject

* fix: update docker docs to match current config

* fix: migrate examples to readme

* fix: add llmcompressor to conflict

* feat: rec uv sync with lockfile for dev/ci

* fix: update docker docs to clarify how to use uv images

* chore: docs

* fix: use system python, no venv

* fix: set backend cpu

* fix: only set for installing pytorch step

* fix: remove unsloth kernel and installs

* fix: remove U in tests

* fix: set backend in deps too

* chore: test

* chore: comments

* fix: attempt to lock torch

* fix: workaround torch cuda and not upgraded

* fix: forgot to push

* fix: missed source

* fix: nightly upstream loralinear config

* fix: nightly phi3 long rope not work

* fix: forgot commit

* fix: test phi3 template change

* fix: no more requirements

* fix: carry over changes from new requirements to pyproject

* chore: remove lockfile per discussion

* fix: set match-runtime

* fix: remove unneeded hf hub buildtime

* fix: duplicate cache delete on nightly

* fix: torchvision being overridden

* fix: migrate to uv images

* fix: leftover from merge

* fix: simplify base readme

* fix: update assertion message to be clearer

* chore: docs

* fix: change fallback for cicd script

* fix: match against main exactly

* fix: peft 0.19.1 change

* fix: e2e test

* fix: ci

* fix: e2e test
2026-04-21 10:16:03 -04:00

257 lines
5.3 KiB
TOML

[build-system]
requires = ["setuptools>=64", "wheel", "setuptools_scm>=8"]
build-backend = "setuptools.build_meta"
[project]
name = "axolotl"
dynamic = ["version"]
description = "LLM Trainer"
readme = "README.md"
requires-python = ">=3.10"
# license = "Apache-2.0"
dependencies = [
# Core ML stack
"torch>=2.6.0",
"packaging==26.0",
"huggingface_hub>=1.1.7",
"peft>=0.19.1,<0.20.0",
"tokenizers>=0.22.1",
"transformers==5.5.4",
"accelerate==1.13.0",
"datasets>=4.8.4,<4.9.0",
"trl==1.1.0",
"hf_xet==1.4.3",
"kernels==0.13.0",
"trackio>=0.16.1",
"typing-extensions>=4.15.0",
"optimum==1.16.2",
"hf_transfer",
"sentencepiece",
"gradio>=6.2.0,<7.0",
"modal==1.3.0.post1",
"pydantic>=2.10.6",
"addict",
"fire",
"PyYAML>=6.0",
"requests",
"wandb",
"einops",
"colorama",
"numba>=0.61.2",
"numpy>=2.2.6",
# Evaluation & metrics
"evaluate==0.4.1",
"scipy",
"nvidia-ml-py==12.560.30",
"art",
"tensorboard",
"python-dotenv==1.0.1",
# Remote filesystems
"s3fs>=2024.5.0",
"gcsfs>=2025.3.0",
"adlfs>=2024.5.0",
"ocifs==1.3.2",
"zstandard==0.22.0",
"fastcore",
# lm eval harness
"lm_eval==0.4.11",
"langdetect==1.0.9",
"immutabledict==4.2.0",
"antlr4-python3-runtime==4.13.2",
"schedulefree==1.4.1",
"openenv-core==0.1.0",
# Axolotl contribs
"axolotl-contribs-lgpl==0.0.7",
"axolotl-contribs-mit==0.0.6",
# Telemetry
"posthog==6.7.11",
"mistral-common==1.11.0",
# Platform-specific (Linux only)
"bitsandbytes==0.49.1 ; sys_platform != 'darwin'",
"triton>=3.4.0 ; sys_platform != 'darwin'",
"xformers>=0.0.23.post1 ; sys_platform != 'darwin'",
"liger-kernel==0.7.0 ; sys_platform != 'darwin'",
"torchao==0.17.0 ; sys_platform != 'darwin' and platform_machine != 'aarch64'",
# Architecture-specific
"fla-core==0.4.1 ; platform_machine != 'aarch64'",
"flash-linear-attention==0.4.1 ; platform_machine != 'aarch64'",
]
[project.optional-dependencies]
flash-attn = ["flash-attn==2.8.3"]
ring-flash-attn = [
"flash-attn==2.8.3",
"ring-flash-attn>=0.1.7",
]
deepspeed = [
"deepspeed>=0.18.6,<0.19.0",
"deepspeed-kernels",
]
mamba-ssm = [
"mamba-ssm==1.2.0.post1",
"causal_conv1d",
]
auto-gptq = [
"auto-gptq==0.5.1",
]
mlflow = [
"mlflow",
]
galore = [
"galore_torch",
]
apollo = [
"apollo-torch",
]
optimizers = [
"galore_torch",
"apollo-torch",
"lomo-optim==0.1.1",
"torch-optimi==0.2.1",
"came_pytorch==0.1.3",
]
ray = [
"ray[train]>=2.52.1",
]
vllm = [
"vllm>=0.15.0",
]
llmcompressor = [
"llmcompressor>=0.10.0",
]
fbgemm-gpu = ["fbgemm-gpu-genai>=1.3.0"]
opentelemetry = [
"opentelemetry-api",
"opentelemetry-sdk",
"opentelemetry-exporter-prometheus",
"prometheus-client",
]
[dependency-groups]
dev = [
"black",
"mypy",
"pre-commit",
"types-requests",
"quartodoc",
"jupyter",
"blobfile",
"tiktoken",
]
test = [
"codecov",
"codecov-cli",
"pytest",
"pytest-cov",
"pytest-retry",
"pytest-sugar",
"pytest-xdist",
"tbparse",
]
[project.scripts]
axolotl = "axolotl.cli.main:main"
[project.urls]
Homepage = "https://axolotl.ai/"
Documentation = "https://docs.axolotl.ai/"
Repository = "https://github.com/axolotl-ai-cloud/axolotl.git"
[tool.setuptools]
include-package-data = true
[tool.setuptools.packages.find]
where = ["src"]
[tool.setuptools.dynamic]
version = { file = "VERSION" }
[tool.ruff]
line-length = 88
target-version = "py310"
[tool.ruff.lint]
select = ["E", "F", "W", "C90", "B", "I"]
ignore = [
"E203", # Whitespace before ':'
"E501", # Line too long
"C901", # Too complex
"B019", # Use of functools.cache on methods
"E722", # Bare except
"F821", # Undefined name (for dynamic exec)
]
[tool.ruff.lint.isort]
known-third-party = ["wandb", "comet_ml"]
known-local-folder = ["src", "tests"]
# Black-compatible isort settings
force-single-line = false
combine-as-imports = true
split-on-trailing-comma = true
[tool.ruff.format]
# Use black's formatting style exactly
quote-style = "double"
indent-style = "space"
skip-magic-trailing-comma = false
line-ending = "auto"
docstring-code-format = false
[tool.pytest.ini_options]
addopts = "-m 'not slow'"
markers = [
"slow: marks tests as slow",
]
# UV specific configuration
[tool.uv]
prerelease = "allow"
conflicts = [
[
{ package = "axolotl" },
{ extra = "vllm" },
],
[
{ package = "axolotl" },
{ extra = "flash-attn" },
],
[
{ package = "axolotl" },
{ extra = "ring-flash-attn" },
],
[
{ package = "axolotl" },
{ extra = "mamba-ssm" },
],
[
{ package = "axolotl" },
{ extra = "auto-gptq" },
],
[
{ package = "axolotl" },
{ extra = "fbgemm-gpu" },
],
[
{ package = "axolotl" },
{ extra = "llmcompressor" },
],
]
[tool.uv.extra-build-dependencies]
mamba-ssm = [{ requirement = "torch", match-runtime = true }]
causal-conv1d = [{ requirement = "torch", match-runtime = true }]
flash-attn = [{ requirement = "torch", match-runtime = true }]
deepspeed = [{ requirement = "torch", match-runtime = true }]
auto-gptq = [{ requirement = "torch", match-runtime = true }]