High Performance Quantative Finance Library on JAX
Project description
JAX-Quant-Finance: High Performance Quantative Finance on JAX
Introduction
Inspired by TF Quant Finance, we developed a quantative finance library based on JAX. This library provides high-performance components leveraging the hardware acceleration, parallel scientific computing and automatic differentiation of JAX.
We can:
-
run financial workloads on CPU/GPU/TPU with XLA acceleration
-
calculate mathematical derivative of financial models, i.e. Greeks
-
distribute workloads on multiple devices and machines
examples
directory contains several demonstrations of using the JAX-Quant-Finance.
Install
JAX installation
You must first follow JAX's installation guide to install JAX based on your device architecture (CPU/GPU/TPU).
JAX-Quant-Finance
pip install jax-quant-finance --upgrade
64-bit precision
To enable 64-bit precision, set the respective JAX flag before importing jax_quant_finance
(see the JAX guide), for example:
from jax.config import config
config.update("jax_enable_x64", True)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for jax_quant_finance-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 11ae8f623d1c857b3159405bb297027a390da8505251cda9268363d5248a6d86 |
|
MD5 | c2f285f6c4c56144604eea2cfc41e542 |
|
BLAKE2b-256 | 45d4270d47348e011f9b419052a6ae58aa3d35cc04f8dafc1327a285ca2b4066 |