deepseek-v4.1IMAGE
int21_ai claims Rust inference stack hits 1,700+ tok/s on DeepSeek V4.1 Flash
int21_ai says its generated Rust Inference Factory beats vLLM and SGLang across 20+ models, reaching over 1,700 tokens/s on DeepSeek V4.1 Flash.
Bing Xu
@bingxu_Archived 9 days agoOriginally posted 2026.10.23
Bing Xu @bingxu_Originally posted 2026.10.23
This shows just how challenging it was to build @int21_ai 's Rust Inference Factory. We generated the entire stack and outperformed vLLM and SGLang across 20+ models in ultra-fast mode, including achieving over 1,700 tokens/s on DeepSeek v4.1 Flash inference.
x.com/bingxu_/status/2113324885598699552Archived 2026.10.23 12:08