port-bio-model-to-tenstorrent

Port biomolecular models to Tenstorrent hardware within the tt-bio stack.

118|12|Updated Mar 23, 2025

Search Tags:#port #on-device #structure-prediction #vendoring #tenstorrent #biomolecular #tt-bio

Ready to run

npx skills add https://github.com/moritztng/tt-bio --skill port-bio-model-to-tenstorrent

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: port-bio-model-to-tenstorrent
Source: https://github.com/moritztng/tt-bio/tree/main/.claude/skills/port-bio-model-to-tenstorrent
Command: npx skills add https://github.com/moritztng/tt-bio --skill port-bio-model-to-tenstorrent

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Port biomolecular models to Tenstorrent hardware within the tt-bio codebase, delivering a reproducible, inference-only porting playbook that enforces vendored dependencies and a unified integration pattern.

Core Features & Use Cases

Standard porting workflow for biomolecular models (protein folding, structure prediction, LM-based components) to Tenstorrent;
Phase-driven process with parity testing, residency, and documentation folding;
Vendored references and a single shared integration layer to minimize debt and duplication.

Quick Start

Follow the Port a bio model to Tenstorrent workflow to port a new biomolecular model into tt-bio on Tenstorrent hardware.

Frequently Asked Questions about port-bio-model-to-tenstorrent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I port a biomolecular model to Tenstorrent hardware?▼

Porting protein folding and structure prediction models to Tenstorrent hardware uses a phase-driven workflow within the tt-bio stack, enforcing inference-only code, vendored dependencies, and parity testing for unified device integration.

What is on-device residency for biomolecular structure prediction?▼

On-device residency for biomolecular structure prediction ensures that the entire inference workflow of ported architectures runs natively on Tenstorrent hardware. This is a non-negotiable requirement enforced during the tt-bio integration process.

Can I use training code when porting protein folding models to Tenstorrent?▼

No, you cannot use training code when porting protein folding models to Tenstorrent. The tt-bio stack enforces a strict zero training code requirement, allowing exclusively inference-only implementations for biomolecular architectures.

Do I need to vendor dependencies for ESMFold2 inspired architectures on Tenstorrent?▼

Yes, you must vendor dependencies for ESMFold2 inspired architectures on Tenstorrent. The tt-bio stack mandates vendored dependencies to minimize technical debt and ensure reproducible inference-only porting.

How does parity testing work for LM-based components ported to Tenstorrent?▼

Parity testing for LM-based components ported to Tenstorrent validates that the hardware implementation matches reference model outputs. This testing phase is mandated within the tt-bio stack to achieve unified integration.

What are the limitations when porting Boltz-2 architectures to Tenstorrent hardware?▼

Limitations when porting Boltz-2 architectures include a strict requirement for zero training code and mandatory bf16 or fast mode support. The porting process enforces these constraints to maintain a single shared integration layer.