Manage the Python module with maturin

This commit is contained in:
konstin 2025-10-31 15:58:05 +01:00
parent dfc88334b6
commit 3b372875c1
4 changed files with 20 additions and 15 deletions

1
.gitignore vendored
View File

@ -1,6 +1,7 @@
.venv/ .venv/
__pycache__/ __pycache__/
*.pyc *.pyc
*.so
rustbpe/target/ rustbpe/target/
dev-ignore/ dev-ignore/
report.md report.md

View File

@ -149,7 +149,7 @@ class HuggingFaceTokenizer:
# ----------------------------------------------------------------------------- # -----------------------------------------------------------------------------
# Tokenizer based on rustbpe + tiktoken combo # Tokenizer based on rustbpe + tiktoken combo
import pickle import pickle
import rustbpe from nanochat import rustbpe
import tiktoken import tiktoken
class RustBPETokenizer: class RustBPETokenizer:

View File

@ -23,7 +23,7 @@ requires = ["maturin>=1.7,<2.0"]
build-backend = "maturin" build-backend = "maturin"
[tool.maturin] [tool.maturin]
module-name = "rustbpe" module-name = "nanochat.rustbpe"
bindings = "pyo3" bindings = "pyo3"
python-source = "." python-source = "."
manifest-path = "rustbpe/Cargo.toml" manifest-path = "rustbpe/Cargo.toml"
@ -67,9 +67,15 @@ cpu = [
gpu = [ gpu = [
"torch>=2.8.0", "torch>=2.8.0",
] ]
[tool.uv] [tool.uv]
conflicts = [ cache-keys = [
{ file = "pyproject.toml" },
{ file = "rustbpe/src/**/*.rs" },
{ file = "rustbpe/Cargo.toml" },
{ file = "rustbpe/Cargo.lock" }
]
conflicts = [
[ [
{ extra = "cpu" }, { extra = "cpu" },
{ extra = "gpu" }, { extra = "gpu" },

18
uv.lock
View File

@ -311,7 +311,7 @@ name = "exceptiongroup"
version = "1.3.0" version = "1.3.0"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
dependencies = [ dependencies = [
{ name = "typing-extensions", marker = "python_full_version < '3.12' or (extra == 'extra-8-nanochat-cpu' and extra == 'extra-8-nanochat-gpu')" }, { name = "typing-extensions", marker = "python_full_version < '3.11' or (extra == 'extra-8-nanochat-cpu' and extra == 'extra-8-nanochat-gpu')" },
] ]
sdist = { url = "https://files.pythonhosted.org/packages/0b/9f/a65090624ecf468cdca03533906e7c69ed7588582240cfe7cc9e770b50eb/exceptiongroup-1.3.0.tar.gz", hash = "sha256:b241f5885f560bc56a59ee63ca4c6a8bfa46ae4ad651af316d4e81817bb9fd88", size = 29749, upload-time = "2025-05-10T17:42:51.123Z" } sdist = { url = "https://files.pythonhosted.org/packages/0b/9f/a65090624ecf468cdca03533906e7c69ed7588582240cfe7cc9e770b50eb/exceptiongroup-1.3.0.tar.gz", hash = "sha256:b241f5885f560bc56a59ee63ca4c6a8bfa46ae4ad651af316d4e81817bb9fd88", size = 29749, upload-time = "2025-05-10T17:42:51.123Z" }
wheels = [ wheels = [
@ -777,7 +777,6 @@ dependencies = [
{ name = "datasets" }, { name = "datasets" },
{ name = "fastapi" }, { name = "fastapi" },
{ name = "files-to-prompt" }, { name = "files-to-prompt" },
{ name = "numpy" },
{ name = "psutil" }, { name = "psutil" },
{ name = "regex" }, { name = "regex" },
{ name = "setuptools" }, { name = "setuptools" },
@ -811,7 +810,6 @@ requires-dist = [
{ name = "datasets", specifier = ">=4.0.0" }, { name = "datasets", specifier = ">=4.0.0" },
{ name = "fastapi", specifier = ">=0.117.1" }, { name = "fastapi", specifier = ">=0.117.1" },
{ name = "files-to-prompt", specifier = ">=0.6" }, { name = "files-to-prompt", specifier = ">=0.6" },
{ name = "numpy", specifier = "==1.26.4" },
{ name = "psutil", specifier = ">=7.1.0" }, { name = "psutil", specifier = ">=7.1.0" },
{ name = "regex", specifier = ">=2025.9.1" }, { name = "regex", specifier = ">=2025.9.1" },
{ name = "setuptools", specifier = ">=80.9.0" }, { name = "setuptools", specifier = ">=80.9.0" },
@ -951,7 +949,7 @@ name = "nvidia-cudnn-cu12"
version = "9.10.2.21" version = "9.10.2.21"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
dependencies = [ dependencies = [
{ name = "nvidia-cublas-cu12", marker = "extra == 'extra-8-nanochat-gpu'" }, { name = "nvidia-cublas-cu12", marker = "(sys_platform == 'linux' and extra == 'extra-8-nanochat-gpu') or (extra == 'extra-8-nanochat-cpu' and extra == 'extra-8-nanochat-gpu')" },
] ]
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/fa/41/e79269ce215c857c935fd86bcfe91a451a584dfc27f1e068f568b9ad1ab7/nvidia_cudnn_cu12-9.10.2.21-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:c9132cc3f8958447b4910a1720036d9eff5928cc3179b0a51fb6d167c6cc87d8", size = 705026878, upload-time = "2025-06-06T21:52:51.348Z" }, { url = "https://files.pythonhosted.org/packages/fa/41/e79269ce215c857c935fd86bcfe91a451a584dfc27f1e068f568b9ad1ab7/nvidia_cudnn_cu12-9.10.2.21-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:c9132cc3f8958447b4910a1720036d9eff5928cc3179b0a51fb6d167c6cc87d8", size = 705026878, upload-time = "2025-06-06T21:52:51.348Z" },
@ -964,7 +962,7 @@ name = "nvidia-cufft-cu12"
version = "11.3.3.83" version = "11.3.3.83"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
dependencies = [ dependencies = [
{ name = "nvidia-nvjitlink-cu12", marker = "extra == 'extra-8-nanochat-gpu'" }, { name = "nvidia-nvjitlink-cu12", marker = "(sys_platform == 'linux' and extra == 'extra-8-nanochat-gpu') or (extra == 'extra-8-nanochat-cpu' and extra == 'extra-8-nanochat-gpu')" },
] ]
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/60/bc/7771846d3a0272026c416fbb7e5f4c1f146d6d80704534d0b187dd6f4800/nvidia_cufft_cu12-11.3.3.83-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:848ef7224d6305cdb2a4df928759dca7b1201874787083b6e7550dd6765ce69a", size = 193109211, upload-time = "2025-03-07T01:44:56.873Z" }, { url = "https://files.pythonhosted.org/packages/60/bc/7771846d3a0272026c416fbb7e5f4c1f146d6d80704534d0b187dd6f4800/nvidia_cufft_cu12-11.3.3.83-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:848ef7224d6305cdb2a4df928759dca7b1201874787083b6e7550dd6765ce69a", size = 193109211, upload-time = "2025-03-07T01:44:56.873Z" },
@ -996,9 +994,9 @@ name = "nvidia-cusolver-cu12"
version = "11.7.3.90" version = "11.7.3.90"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
dependencies = [ dependencies = [
{ name = "nvidia-cublas-cu12", marker = "extra == 'extra-8-nanochat-gpu'" }, { name = "nvidia-cublas-cu12", marker = "(sys_platform == 'linux' and extra == 'extra-8-nanochat-gpu') or (extra == 'extra-8-nanochat-cpu' and extra == 'extra-8-nanochat-gpu')" },
{ name = "nvidia-cusparse-cu12", marker = "extra == 'extra-8-nanochat-gpu'" }, { name = "nvidia-cusparse-cu12", marker = "(sys_platform == 'linux' and extra == 'extra-8-nanochat-gpu') or (extra == 'extra-8-nanochat-cpu' and extra == 'extra-8-nanochat-gpu')" },
{ name = "nvidia-nvjitlink-cu12", marker = "extra == 'extra-8-nanochat-gpu'" }, { name = "nvidia-nvjitlink-cu12", marker = "(sys_platform == 'linux' and extra == 'extra-8-nanochat-gpu') or (extra == 'extra-8-nanochat-cpu' and extra == 'extra-8-nanochat-gpu')" },
] ]
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/c8/32/f7cd6ce8a7690544d084ea21c26e910a97e077c9b7f07bf5de623ee19981/nvidia_cusolver_cu12-11.7.3.90-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:db9ed69dbef9715071232caa9b69c52ac7de3a95773c2db65bdba85916e4e5c0", size = 267229841, upload-time = "2025-03-07T01:46:54.356Z" }, { url = "https://files.pythonhosted.org/packages/c8/32/f7cd6ce8a7690544d084ea21c26e910a97e077c9b7f07bf5de623ee19981/nvidia_cusolver_cu12-11.7.3.90-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:db9ed69dbef9715071232caa9b69c52ac7de3a95773c2db65bdba85916e4e5c0", size = 267229841, upload-time = "2025-03-07T01:46:54.356Z" },
@ -1011,7 +1009,7 @@ name = "nvidia-cusparse-cu12"
version = "12.5.8.93" version = "12.5.8.93"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
dependencies = [ dependencies = [
{ name = "nvidia-nvjitlink-cu12", marker = "extra == 'extra-8-nanochat-gpu'" }, { name = "nvidia-nvjitlink-cu12", marker = "(sys_platform == 'linux' and extra == 'extra-8-nanochat-gpu') or (extra == 'extra-8-nanochat-cpu' and extra == 'extra-8-nanochat-gpu')" },
] ]
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/bc/f7/cd777c4109681367721b00a106f491e0d0d15cfa1fd59672ce580ce42a97/nvidia_cusparse_cu12-12.5.8.93-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:9b6c161cb130be1a07a27ea6923df8141f3c295852f4b260c65f18f3e0a091dc", size = 288117129, upload-time = "2025-03-07T01:47:40.407Z" }, { url = "https://files.pythonhosted.org/packages/bc/f7/cd777c4109681367721b00a106f491e0d0d15cfa1fd59672ce580ce42a97/nvidia_cusparse_cu12-12.5.8.93-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:9b6c161cb130be1a07a27ea6923df8141f3c295852f4b260c65f18f3e0a091dc", size = 288117129, upload-time = "2025-03-07T01:47:40.407Z" },
@ -1955,7 +1953,7 @@ name = "triton"
version = "3.4.0" version = "3.4.0"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
dependencies = [ dependencies = [
{ name = "setuptools", marker = "extra == 'extra-8-nanochat-gpu'" }, { name = "setuptools", marker = "(sys_platform == 'linux' and extra == 'extra-8-nanochat-gpu') or (extra == 'extra-8-nanochat-cpu' and extra == 'extra-8-nanochat-gpu')" },
] ]
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/62/ee/0ee5f64a87eeda19bbad9bc54ae5ca5b98186ed00055281fd40fb4beb10e/triton-3.4.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7ff2785de9bc02f500e085420273bb5cc9c9bb767584a4aa28d6e360cec70128", size = 155430069, upload-time = "2025-07-30T19:58:21.715Z" }, { url = "https://files.pythonhosted.org/packages/62/ee/0ee5f64a87eeda19bbad9bc54ae5ca5b98186ed00055281fd40fb4beb10e/triton-3.4.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7ff2785de9bc02f500e085420273bb5cc9c9bb767584a4aa28d6e360cec70128", size = 155430069, upload-time = "2025-07-30T19:58:21.715Z" },