Wire flash
Moore Threads completes full-pipeline inference support for open-source biology model Protenix-v2
Editorial responsibility
- No named human review is recorded for this page.
- Source reporting is collected, normalized, translated or condensed automatically when needed.
- Automatically published source-backed update
Moore Threads, a Chinese GPU company, announced on September 24 that it has completed full-pipeline inference support for the open-source biomolecular structure prediction model Protenix-v2 on its MTT S5000 training-inference card, based on its proprietary MUSA software stack. According to the company's tests, the S5000 achieves an average 26% speedup in end-to-end inference performance compared to international mainstream GPUs, while maintaining high alignment in 3D conformation prediction accuracy. Protenix-v2 was developed by ByteDance's Seed team and released in April 2026. The model is noted for breaking restrictions of overseas top-tier models that do not fully open their weights or allow private deployment, and is one of the few open-source foundation models capable of high-precision end-to-end prediction of complexes involving proteins, DNA, RNA, and small-molecule ligands.
Source report
September 24 — Moore Threads has recently completed full-chain inference support for the open-source biomolecular structure prediction model Protenix-v2, based on its proprietary MUSA software stack and running on the MTT S5000 training-inference integrated AI computing card.
According to real-world testing, the end-to-end inference performance of the MTT S5000 is on average approximately 26% faster than mainstream international GPUs. Additionally, the accuracy of its three-dimensional conformation predictions is highly aligned with benchmark standards.
About Protenix-v2
- Developed by ByteDance's Seed team
- Officially released in April 2026
- Breaks the limitations of overseas top-tier models, which often have incomplete open-source weights and cannot be deployed privately
- One of the few open-source foundation models globally capable of high-precision end-to-end prediction of complexes involving proteins, DNA, RNA, and small-molecule ligands
(Source: Securities Times)
Source
金十数据Eastern
Part of this Story
Moore Threads MTT S5000 runs Protenix-v2 26% faster than international GPUs