Novita AI
@novita_labs
AI & Agent Cloud for Developers
⚡Join our community:
가입 September 2023
415 팔로잉 중 5.7K 팬
Open source will win!
🚀 vLLM's Humming backend can run Chord, @novita_labs' open-source W4A16 MoE kernels for Kimi K2.x.
Kernel gains reach 1.33x on H200 TP8 vs tuned public Humming and 2.15x on B300 EP8 decode vs its untuned default.
The indexed path works on compatible vLLM revisions; grouped integration is WIP. Great to see the kernels and benchmarks open-sourced!
Details:
더 보기
