# google/tf-quant-finance

High-performance TensorFlow library for quantitative finance.

Repository: https://github.com/google/tf-quant-finance
Canonical: https://ross.abutalabs.com/products/tf-quant-finance
Language: Python
License: Apache-2.0
License Family: permissive
Topics: tensorflow, quantitative-finance, python, finance, numerical-methods, numerical-optimization, numerical-integration, high-performance, high-performance-computing, gpu, gpu-computing, quantlib
Last push: 2026-08-06T22:18:59+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 8, longevity 100
- inputs: {"age_days": 2597, "days_push": 27, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5480, forks 694 (observed 2026-08-28T04:09:19.710357+00:00)

## What it is
A high-performance TensorFlow library for quantitative finance providing foundational numerical methods, ODE/PDE solvers, and pricing models like Local Vol and Hull-White with GPU acceleration and automatic differentiation. The project has been archived and is no longer maintained by Google.

## Use cases
- price options with local volatility and stochastic volatility models in TensorFlow
- calibrate interest rate models like Hull-White on GPU
- solve PDEs for derivative pricing
- generate quasi-random numbers for Monte Carlo simulation
- build rate curves and generate schedules for fixed income analytics
- run quantitative finance computations with automatic differentiation

## When to choose
- you need GPU-accelerated derivative pricing within a TensorFlow ecosystem
- you want automatic differentiation for calibration and risk sensitivities
- you are willing to fork and maintain the code yourself since it is archived

## When to avoid
- you need a maintained library with active support and bug fixes
- you prefer a general-purpose quant library like QuantLib without TensorFlow dependency
- your stack is PyTorch or JAX rather than TensorFlow

## Facets
- artifact type: library
- maturity: abandoned
- function: math, machine-learning, gpu-computing, simulation
- domain: fintech, mathematics, machine-learning
- platform: python, cross-platform
- tags: quantitative-finance, tensorflow, option-pricing, numerical-methods, pde-solvers, stochastic-modeling, archived, gpu

## Member repositories
- google/tf-quant-finance (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:19.710357+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:56:23.134264+00:00, confidence not recorded.
  - readme: https://github.com/google/tf-quant-finance (fetched 2026-08-28T04:09:19.710357+00:00, sha 0bafa97c6fa0)
  - registry_pypi: https://pypi.org/pypi/tf-quant-finance/json (fetched 2026-08-29T08:51:39.847569+00:00, sha 4dd0ebe43e38)
- Data as of 2026-08-30T08:39:29.467469+00:00.