Add fused GatedDeltaNet decode Triton kernel#18865

Merged

Gasoonjia merged 61 commits intomainfrom

fused-deltanet-decode

Apr 27, 2026

Commits on Apr 2, 2026

Replace chunked FLA with recurrent gated delta rule for T=1 decode
Gasoonjia
committed

Commits on Apr 5, 2026

Dual-method PTE with GPU-resident state for Qwen3.5 MoE
gasoonjia
committed

Commits on Apr 6, 2026

Use share_mutable_buffers to eliminate select_scatter overhead
gasoonjia
committed
Merge branch 'main' into recurrent-fla

Gasoonjia
authored and
gasoonjia
committed
lint
Gasoonjia
committed
remove reduntdant updates
Gasoonjia
committed

Commits on Apr 7, 2026

Commits on Apr 9, 2026

Improve CUDA backend error handling and add dual-method runner fallback
gasoonjia
committed

Commits on Apr 10, 2026

Commits on Apr 13, 2026

Commits on Apr 14, 2026

Add fused GatedDeltaNet decode Triton kernel
Gasoonjia
committed

Commits on Apr 17, 2026

solve stride out of scope
Gasoonjia
committed

Commits on Apr 21, 2026

Merge branch 'main' into cuda-graph
Gasoonjia
authored

Commits on Apr 22, 2026

Commits on Apr 23, 2026