Moore Threads enables full-link inference support for Protenix-v2 on MTT S5000
According to 36Kr, Moore Threads has completed end-to-end inference support for Protenix-v2 on the MTT S5000 AI computing card using its in-house MUSA software stack. In testing, the S5000 achieved about 26% faster end-to-end inference than international mainstream GPUs, with 3D conformation prediction accuracy closely aligned. Protenix-v2, developed by ByteDance Seed team, was released in April 2026 and is an open-source foundation capable of high-precision end-to-end predictions for proteins, DNA, RNA, and small molecule ligand complexes.
Key facts
- 01MTT S5000 runs on the MUSA software stack.
- 02End-to-end inference speedup is about 26% versus international mainstream GPUs.
- 03Protenix-v2 was released in April 2026 by ByteDance Seed team.
- 04Protenix-v2 can predict proteins, DNA, RNA, and small molecule ligand complexes, as an open-source base.
AI-generated from the sources below. Always check the originals.
How each country tells it
So far our sources show coverage from one country. Perspectives appear once we find reports from a second country.
Sources
Summaries are AI-generated from the linked sources and may contain errors; always check the originals. We summarise and link; we never republish articles. Photos come from openly licensed libraries, official publicity material and brand logos, credited to their sources. If you own an image and want it credited differently or removed, email info@coda.news and we will act promptly.