Asari AI(@AsariAILabs):Our self-improving agents optimized the full @vLLM_project inference stack, with up to 16% more throughput and interactivity for @deepseek_ai v4 Pro and @Zai_org GLM 5.2 on B200s (no MTP). Every change was verified and our agents got better and faster at it with each iteration.

Asari AI

@AsariAILabs

Co-invent the future -- learn more: -- we're hiring!

加入 November 2023

16 正在關注 1.4K 粉絲

Asari AI@AsariAILabs

2026.07.29 17:24

Our self-improving agents optimized the full @vLLM_project inference stack, with up to 16% more throughput and interactivity for @deepseek_ai v4 Pro and @Zai_org GLM 5.2 on B200s (no MTP). Every change was verified and our agents got better and faster at it with each iteration.