LMSYS Org
@lmsysorg
SGLang day-0 speed on Kimi K3: 423 tok/s (measured on gsm8k), plus RL support ready in Miles @radixark!
How the largest open-source model runs this fast: we natively implemented and deeply optimized K3’s new architecture with fused KDA decode kernels, DP attention, DSpark, PD
How the largest open-source model runs this fast: we natively implemented and deeply optimized K3’s new architecture with fused KDA decode kernels, DP attention, DSpark, PD
0:53
Kimi.ai@Kimi_Moonshot · Jul 27Releasing the model weights and technical report of Kimi K3.
Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window.
New model architecture: 2.5x the intelligence per unit of compute, not just more params.
Alongside
Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window.
New model architecture: 2.5x the intelligence per unit of compute, not just more params.
Alongside
Open quoted post →
37 375