Gaurav Garg 5a460dea9f Remove redundant CUDA copies after gated_delta_net. (#23940) ...

* Remove redundant CUDA copies after gated_delta_net.

Currently, GDN writes recurrent state snapshots into its output tail, then the graph immediately copies those snapshots into ssm_states_all. With MTP draft length 3, target decode uses K=4, so that becomes 4 extra ggml_cuda_cpy calls.

The change detects that gated_delta_net -> view -> cpy pattern and makes the CUDA GDN kernel write the state snapshot(s) directly into the recurrent cache, skipping the intermediate tail writes and copy kernels when safe.

* Address review comments

2026-07-03 14:36:29 +05:30

..

cmake

ggml : Parallelize quant LUT init (#23595)

2026-05-25 10:15:46 +03:00

include

sycl : support --split-mode tensor (#24152)

2026-06-25 08:35:21 +03:00

src

Remove redundant CUDA copies after gated_delta_net. (#23940)

2026-07-03 14:36:29 +05:30

.gitignore

vulkan : cmake integration (#8119)

2024-07-13 18:12:39 +02:00

CMakeLists.txt

ggml : bump version to 0.15.3 (ggml/1550)

2026-06-26 15:04:42 +03:00