Fast-Vollib: A Fast Implied Volatility Library for Pythonwith PyTorch, JAX, and CUDA Fused-Kernel Backends

2026-04-29

AI Summary

This work addresses the demand in financial engineering for high-performance, batch computation of European option prices, implied volatilities (IV), and Greeks by introducing an efficient Python library fully compatible with py_vollib. It presents the first open-source implementation integrating a fully vectorized version of Jäckel’s “Let’s Be Rational” algorithm, augmented with Halley’s method to accelerate IV inversion. By unifying multiple backends—including NumPy/Numba, PyTorch, JAX, and Triton CUDA fused kernels—the library enables torch.compile optimization and single-pass GPU kernels, substantially enhancing computational efficiency for large-scale option chains. While preserving strict API compatibility with existing tools, the proposed library achieves state-of-the-art performance in batch processing, setting a new benchmark for scalable quantitative finance workflows.

Abstract

We present fast-vollib, an open-source Python library that provides high-performance European option pricing, implied volatility (IV) computation, and Greeks under the Black-76, Black-Scholes, and Black-Scholes-Merton models. The library is designed as a drop-in alternative to the de-facto-standard py_vollib and py_vollib_vectorized packages, with pluggable PyTorch and JAX execution backends, a CUDA fused-kernel Triton contribution for batched IV workloads, and a compatibility-first public API. In addition to a vectorized Halley-method IV solver, fast-vollib ships an experimental, fully-vectorized implementation of Jäckel's "Let's Be Rational" (LBR) algorithm with NumPy/Numba, torch.compile, JAX, and Triton single-pass GPU kernels for batched option chains. This note announces the library and describes its public API surface, with source, documentation, and packaging artifacts available at: GitHub (https://github.com/raeidsaqur/fast-vollib), Docs (https://raeidsaqur.github.io/fast-vollib/), PyPI (https://pypi.org/project/fast-vollib/).

Problem

• implied volatility
• option pricing
• computational performance
• batched computation
• financial derivatives

Innovation

• implied volatility
• GPU acceleration
• vectorized computation
• Triton fused-kernel
• Jäckel's LBR algorithm