llama.cpp/ggml
Jeff Bolz e592be1575
vulkan: fix rms_norm+mul fusion (#14545)
The fused operation was grabbing the epsilon value from the wrong place.

Add an env var to disable fusion.

Add some missing checks for supported shapes/types.

Handle fused rms_norm+mul in check_results.
2025-07-06 10:08:16 +02:00
..
cmake ggml-cpu : rework weak alias on apple targets (#14146) 2025-06-16 13:54:15 +08:00
include ggml : implement GEGLU_ERF and GEGLU_QUICK ops (#14445) 2025-07-03 23:07:22 +02:00
src vulkan: fix rms_norm+mul fusion (#14545) 2025-07-06 10:08:16 +02:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml : remove kompute backend (#14501) 2025-07-03 07:48:32 +03:00