Skip to main content

LLVM-based compiler for LightGBM models

Project description

lleaves 🍃

CI Documentation Status Downloads

A LLVM-based compiler for LightGBM decision trees.

lleaves converts trained LightGBM models to optimized machine code, speeding-up prediction by ≥10x.

Example

lgbm_model = lightgbm.Booster(model_file="NYC_taxi/model.txt")
%timeit lgbm_model.predict(df)
# 12.77s

llvm_model = lleaves.Model(model_file="NYC_taxi/model.txt")
llvm_model.compile()
%timeit llvm_model.predict(df)
# 0.90s 

Why lleaves?

  • Speed: Both low-latency single-row prediction and high-throughput batch-prediction.
  • Drop-in replacement: The interface of lleaves.Model is a subset of LightGBM.Booster.
  • Dependencies: llvmlite and numpy. LLVM comes statically linked.

Installation

conda install -c conda-forge lleaves or pip install lleaves (Linux and MacOS only).

Benchmarks

Ran on a dedicated Intel i7-4770 Haswell, 4 cores. Stated runtime is the minimum over 20.000 runs.

Dataset: NYC-taxi

mostly numerical features.

batchsize 1 10 100
LightGBM 52.31μs 84.46μs 441.15μs
ONNX Runtime 11.00μs 36.74μs 190.87μs
Treelite 28.03μs 40.81μs 94.14μs
lleaves 9.61μs 14.06μs 31.88μs

Dataset: MTPL2

mix of categorical and numerical features.

batchsize 10,000 100,000 678,000
LightGBM 95.14ms 992.47ms 7034.65ms
ONNX Runtime 38.83ms 381.40ms 2849.42ms
Treelite 38.15ms 414.15ms 2854.10ms
lleaves 5.90ms 56.96ms 388.88ms

Advanced Usage

To avoid expensive recompilation, you can call lleaves.Model.compile() and pass a cache=<filepath> argument. This will store an ELF (Linux) / Mach-O (macOS) file at the given path when the method is first called. Subsequent calls of compile(cache=<same filepath>) will skip compilation and load the stored binary file instead. For more info, see docs.

To eliminate any Python overhead during inference you can link against this generated binary. For an example of how to do this see benchmarks/c_bench/. The function signature might change between major versions.

Development

High-level explanation of the inner workings of the lleaves compiler: link

mamba env create
conda activate lleaves
pip install -e .
pre-commit install
./benchmarks/data/setup_data.sh
pytest -k "not benchmark"

Cite

If you're using lleaves for your research, I'd appreciate if you could cite it. Use:

@software{Boehm_lleaves,
  author = {Boehm, Simon},
  title = {lleaves},
  url = {https://github.com/siboehm/lleaves},
  license = {MIT},
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

lleaves-1.3.0.tar.gz (1.5 MB view details)

Uploaded Source

Built Distribution

lleaves-1.3.0-py3-none-any.whl (22.2 kB view details)

Uploaded Python 3

File details

Details for the file lleaves-1.3.0.tar.gz.

File metadata

  • Download URL: lleaves-1.3.0.tar.gz
  • Upload date:
  • Size: 1.5 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.0 CPython/3.12.7

File hashes

Hashes for lleaves-1.3.0.tar.gz
Algorithm Hash digest
SHA256 b9e3c0b9e6896aa5bfe32192aba039063e3869dbedc44f5bec7a133078597fb1
MD5 6a2b1ce7bac26c8167ee8594e221e212
BLAKE2b-256 1927aca65414fdc25737a5971b7c82ec1d1358cf49ef05adacf6303f84873230

See more details on using hashes here.

File details

Details for the file lleaves-1.3.0-py3-none-any.whl.

File metadata

  • Download URL: lleaves-1.3.0-py3-none-any.whl
  • Upload date:
  • Size: 22.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.0 CPython/3.12.7

File hashes

Hashes for lleaves-1.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c25d37b3240f36daa8cf6b48847a63f7b37ec2f57749b3ce2997d2a9d5544eb5
MD5 044722c59a89632ddee09a8a440b7e20
BLAKE2b-256 ca1e0f076823cc005e6d3569292e16a57c0cb21c9b0a2439c88fa67ec906ea18

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page