prima.cpp/kompute-shaders
Georgi Gerganov 2b3389677a
ggml : refactor rope norm/neox (#7634)
* ggml : unify rope norm/neox (CPU)

* ggml : fix compile warning

* ggml : remove GLM rope mode

ggml-ci

* metal : better rope implementation

ggml-ci

* cuda : better rope implementation

ggml-ci

* naming : n_orig_ctx -> n_ctx_orig

ggml-ci

* dev : add reminders to update backends

ggml-ci

* vulkan : fix ggml_rope_ext() usage

* cuda : fix array size + indents

ggml-ci
2024-06-05 11:29:20 +03:00
..
common.comp
op_add.comp
op_addrow.comp
op_cpy_f16_f16.comp
op_cpy_f16_f32.comp
op_cpy_f32_f16.comp
op_cpy_f32_f32.comp
op_diagmask.comp
op_gelu.comp
op_getrows.comp
op_getrows_f16.comp
op_getrows_f32.comp kompute : implement op_getrows_f32 (#6403) 2024-06-03 08:32:16 +03:00
op_getrows_q4_0.comp
op_getrows_q4_1.comp
op_getrows_q6_k.comp
op_mul.comp
op_mul_mat_f16.comp
op_mul_mat_mat_f32.comp
op_mul_mat_q4_0.comp
op_mul_mat_q4_1.comp
op_mul_mat_q6_k.comp
op_mul_mat_q8_0.comp
op_mul_mv_q_n.comp
op_mul_mv_q_n_pre.comp
op_norm.comp
op_relu.comp
op_rmsnorm.comp
op_rope_f16.comp ggml : refactor rope norm/neox (#7634) 2024-06-05 11:29:20 +03:00
op_rope_f32.comp ggml : refactor rope norm/neox (#7634) 2024-06-05 11:29:20 +03:00
op_scale.comp
op_scale_8.comp
op_silu.comp
op_softmax.comp
rope_common.comp ggml : refactor rope norm/neox (#7634) 2024-06-05 11:29:20 +03:00