Jeff Bolz 257ce2f5c0 vulkan: fuse rms_norm + mul + rope (+ view + set_rows) (llama/16977) ...

This change combines the rms_norm+mul and rope+view+set_rows fusions to
allow fusing the whole sequence together. This comes up in Qwen3, Bailing,
and some other models.

2025-11-09 23:38:03 +02:00

..

cmake

ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (llama/15094)

2025-08-18 20:30:45 +03:00

include

ggml-cpu : bicubic interpolation (llama/16891)

2025-11-09 23:38:03 +02:00

src

vulkan: fuse rms_norm + mul + rope (+ view + set_rows) (llama/16977)

2025-11-09 23:38:03 +02:00

.gitignore

…

CMakeLists.txt

Add experimental ggml-hexagon backend for the Hexagon NPU (llama/16547)

2025-11-09 23:38:03 +02:00