mirror of
https://github.com/karpathy/nanochat.git
synced 2026-03-03 07:50:28 +00:00
50b236fbcc
Capture PyTorch execution traces and CUDA memory snapshots. Traces display detailed CPU and CUDA activity, including individual CUDA kernel calls. CUDA memory snapshots visualize all memory allocations, helping diagnose CUDA out-of-memory errors, investigate memory leaks, or understand GPU memory usage for educational purposes. Enable profiling with the --enable_profiling=True flag in speedrun.sh. See PROFILING.md for documentation and example visualizations.
57 lines
1.1 KiB
TOML
57 lines
1.1 KiB
TOML
[project]
|
|
name = "nanochat"
|
|
version = "0.1.0"
|
|
description = "the minimal full-stack ChatGPT clone"
|
|
readme = "README.md"
|
|
requires-python = ">=3.10"
|
|
dependencies = [
|
|
"datasets>=4.0.0",
|
|
"fastapi>=0.117.1",
|
|
"files-to-prompt>=0.6",
|
|
"matplotlib>=3.0.0",
|
|
"numpy==1.26.4",
|
|
"psutil>=7.1.0",
|
|
"regex>=2025.9.1",
|
|
"tiktoken>=0.11.0",
|
|
"tokenizers>=0.22.0",
|
|
"torch>=2.8.0",
|
|
"uvicorn>=0.36.0",
|
|
"wandb>=0.21.3",
|
|
]
|
|
|
|
[build-system]
|
|
requires = ["maturin>=1.7,<2.0"]
|
|
build-backend = "maturin"
|
|
|
|
# target torch to cuda 12.8
|
|
[tool.uv.sources]
|
|
torch = [
|
|
{ index = "pytorch-cu128" },
|
|
]
|
|
|
|
[[tool.uv.index]]
|
|
name = "pytorch-cu128"
|
|
url = "https://download.pytorch.org/whl/cu128"
|
|
explicit = true
|
|
|
|
[tool.maturin]
|
|
module-name = "rustbpe"
|
|
bindings = "pyo3"
|
|
python-source = "."
|
|
manifest-path = "rustbpe/Cargo.toml"
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"maturin>=1.9.4",
|
|
"pytest>=8.0.0",
|
|
]
|
|
|
|
[tool.pytest.ini_options]
|
|
markers = [
|
|
"slow: marks tests as slow (deselect with '-m \"not slow\"')",
|
|
]
|
|
testpaths = ["tests"]
|
|
python_files = ["test_*.py"]
|
|
python_classes = ["Test*"]
|
|
python_functions = ["test_*"]
|