Suso Fontán(@susofontan):Implemented batching support for footless-orcasaq-2-27B-nvidia-p100. Benchmarks show 40 tok/s at concurrency = 4 running OrcaSAQ-2-27B (@OrcaRouter) on a single NVIDIA Tesla P100. More updates to follow. • Repo: https://t.co/tCNprAlfTo • Demo (pure prose):

Suso Fontán

@susofontan

Software Architect. Side quest: AI research & AI DevOps.

Joined December 2011

134 Following 85 Followers

Suso Fontán@susofontan

2026.10.05 14:52

Implemented batching support for footless-orcasaq-2-27B-nvidia-p100. Benchmarks show 40 tok/s at concurrency = 4 running OrcaSAQ-2-27B (@OrcaRouter) on a single NVIDIA Tesla P100. More updates to follow. • Repo: • Demo (pure prose):

Forward to community

Most Popular Users

930.7K Followers

1.2M Followers

344.2K Followers

The Wall Street Journal

22.3M Followers

6.3M Followers

345.3K Followers

1.1M Followers

1.2M Followers

3.4M Followers

5.4M Followers

2.1M Followers

241.5M Followers

4.2M Followers

26.4M Followers

5.5M Followers