📰 Les actus de Julian maj : 18:03
Filtrer :

Next

  • Rien ce jour-là.

Labos IA

  • FlashQLA: CP-/Bwd-Friendly Fused Linear Attention Kernels for GDN Qwen · 4 h 00

    Following the release of Qwen3-Next, Gated Delta Network (GDN) has become the workhorse attention layer across the Qwen family — from Qwen3-Next-80B-A3B all the way to the subsequent Qwen3.5 / Qwen3.6 series. As models scale to 397A17B / 122A10B / 35B / 27B and context win