Manifold Labs

Targon V2

Posted 7/29/2024

Introducing Targon v2: A Leaner, More Flexible Foundation for Our Future

We're thrilled to announce the release of Targon v2, a significant rewrite of our core infrastructure that sets the stage for exciting developments on our roadmap. This update brings substantial improvements in efficiency and flexibility for Subnet 4 and the entire Bittensor ecosystem.

Key Highlights:

Streamlined Codebase

We've dramatically reduced our codebase from over 3,500 lines of code in v1 to just a little over 1,800 lines of code in v2. This leaner architecture positions us to more nimbly implement future features and improvements.

Enhanced Fairness on Subnet 4 (SN4)

We've addressed the issue of miners buffering tokens on SN4, which was artificially inflating Tokens Per Second (TPS) metrics. In v1, miners were taking in a validator request, and then pausing responses for multiple seconds before sending a large response all at once.

Targon v2 employs Jaro-Winkler Similarity 1 checks to ensure response similarity to ground truth and grades miners on absolute time, moving us closer to a mechanism that rewards only miners who are doing honest and valuable work.

OpenAI Query Schema Integration

Miners now have the flexibility to use the OpenAI Query Schema, opening up alternatives to TGI such as VLLM or other preferred systems. This change promotes greater diversity and innovation in our mining ecosystem. As a miner, you can now choose any inference engine that is compatible with the OpenAI Query Schema. This gives miners freedom to experiment with different infrastructures until they land on one that produces the most accurate results and the quickest speeds.

Looking Ahead: Manifold Roadmap

As we build on the foundation of Targon v2, here's a glimpse of what's coming:

  • Miner Dashboard: A comprehensive tool for miners to assess their performance in real time
  • Targon Hub: A marketplace for validators to sell bandwidth, leveraging the OpenAI query schema. This will be a massive unlock for validators, as entities will be able to sell the intelligence produced on SN4 to any company that is currently using OpenAI or other closed-source models
  • Multiple Model Compatibility: Expanding our support for various AI models, including Llama 3.1 405B
  • Axon Interface: A new interface to streamline subnet development and bridge the gap between web3 and AI developers
  • Enhanced Tooling: Creation of a suite of development tooling for running the entire ecosystem locally and efficiently

We're excited about the possibilities Targon v2 unlocks and look forward to building these new features alongside the Bittensor community.

Footnotes

  1. Jaro-Winkler Similarity is a metric used to measure the similarity between two strings. Introduced in 1990 by William E. Winkler, Jaro-Winkler builds on the original Jaro Similarity by adding a prefix scale that gives more favorable ratings to strings that match from the beginning.


Contact us