Repository navigation

cuda gemma4: the dense family on the shared operators (text, MLX affine 4-bit), decode under CUDA graphs - #1174

Closed

jschmied wants to merge 19 commits into

ashhart:mainfrom

jschmied:cuda-gemma4

Closed

cuda gemma4: the dense family on the shared operators (text, MLX affine 4-bit), decode under CUDA graphs#1174
jschmied wants to merge 19 commits into
ashhart:mainfrom
jschmied:cuda-gemma4

Commits on Oct 18, 2026
- cuda norms: bf16 residual tails with a branch norm, a layer scalar and MLX's rounded rows
  jschmied
  committed
  88fd80f
Commits on Oct 19, 2026
Commits on Oct 20, 2026
- cuda window_attention: head dim 512 over a linear cache, for global attention
  jschmied
  committed
  7424800
Commits on Oct 21, 2026