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

Paper: arXiv 2604.27210

Authors: Raeid Saqur

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/).

Complexity vs Empirical Score

• Math Complexity: 3.0/10
• Empirical Rigor: 8.5/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The document describes a software engineering effort focusing on high-performance library implementation and GPU-based optimization of standard financial models rather than original mathematical derivation. The rigor score is high due to the emphasis on production-ready backends, CUDA/Triton kernels, and clear library integration for practical quantitative finance pipelines.

Research Flowchart

  flowchart TD
    A[Research Goal: Accelerate Option Pricing & IV Computation] --> B[Methodology: Develop Drop-in High-Performance Library]
    B --> C[Inputs: Black-76, BSM Models & Option Chains]
    C --> D[Processes: Vectorized Numerical Solvers & GPU Kernels]
    D --> E[Techniques: Halley-method, LBR Algorithm; PyTorch/JAX/Triton Backends]
    E --> F[Outcomes: Fast-Vollib Package & Open-Source Artifacts]

Cited References (14)

1. The pricing of options and corporate liabilities (1973)
2. The pricing of commodity contracts (1976)
3. A Simple Formula to Compute the Implied Standard Deviation (1988) — link
4. Deep hedging (2019)
5. A Note on a Simple, Accurate Formula to Compute Implied Standard Deviations (1996) — link
6. Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models (2021)
7. Let’s be rational (2015)
8. The Calculation of Implied Variances from the B lack– S choles Model: A Note (1982) — link

0 of 14 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.