vulkan: add imrope w/o check

Author: JJJYmmm

ggml/src/ggml-vulkan/ggml-vulkan.cpp

@@ -1056,6 +1056,7 @@ struct vk_op_rope_push_constants {
     uint32_t s1;
     uint32_t s2;
     int32_t sections[4];
+    uint32_t is_imrope;
     uint32_t is_back;
     uint32_t set_rows_stride;
 };
@@ -9925,6 +9926,8 @@ static void ggml_vk_rope(ggml_backend_vk_context * ctx, vk_context& subctx, cons
         memcpy(sections, (int32_t *) dst->op_params + 11, sizeof(int)*4);
     }
 
+    const bool is_imrope = mode == GGML_ROPE_TYPE_IMROPE;
+
     float corr_dims[2];
     ggml_rope_yarn_corr_dims(n_dims, n_ctx_orig, freq_base, beta_fast, beta_slow, corr_dims);
 
@@ -9946,7 +9949,7 @@ static void ggml_vk_rope(ggml_backend_vk_context * ctx, vk_context& subctx, cons
         (uint32_t)src0->ne[0], (uint32_t)n_dims, freq_scale, (uint32_t)src0->ne[1],
         freq_base, ext_factor, attn_factor, {corr_dims[0], corr_dims[1]}, theta_scale,
         src2 != nullptr, (uint32_t)src0->ne[2], s1, s2,
-        { sections[0], sections[1], sections[2], sections[3] }, backprop, set_rows_stride,
+        { sections[0], sections[1], sections[2], sections[3] }, is_imrope, backprop, set_rows_stride,
     }, dryrun);
 }
 

ggml/src/ggml-vulkan/vulkan-shaders/rope_head.glsl

@@ -27,6 +27,7 @@ layout (push_constant) uniform parameter {
     uint s1;
     uint s2;
     int sections[4];
+    uint is_imrope;
     uint is_back;
     uint set_rows_stride;
 } p;

ggml/src/ggml-vulkan/vulkan-shaders/rope_multi.comp

@@ -32,17 +32,29 @@ void main() {
     const uint sector = (i0 / 2) % sect_dims;
 
     float theta_base = 0.0;
-    if (sector < p.sections[0]) {
-        theta_base = data_pos[channel_x]*pow(p.theta_scale, i0/2.0f);
-    }
-    else if (sector >= p.sections[0] && sector < sec_w) {
-        theta_base = data_pos[channel_x + ne2 * 1]*pow(p.theta_scale, i0/2.0f);
-    }
-    else if (sector >= sec_w && sector < sec_w + p.sections[2]) {
-        theta_base = data_pos[channel_x + ne2 * 2]*pow(p.theta_scale, i0/2.0f);
-    }
-    else if (sector >= sec_w + p.sections[2]) {
-        theta_base = data_pos[channel_x + ne2 * 3]*pow(p.theta_scale, i0/2.0f);
+    if (p.is_imrope) {
+        if (sector % 3 == 1 && sector < 3 * p.sections[1]) {
+            theta_base = data_pos[channel_x + ne2 * 1]*pow(p.theta_scale, i0/2.0f);
+        } else if (sector % 3 == 2 && sector < 3 * p.sections[2]) {
+            theta_base = data_pos[channel_x + ne2 * 2]*pow(p.theta_scale, i0/2.0f);
+        } else if (sector % 3 == 0 && sector < 3 * p.sections[0]) {
+            theta_base = data_pos[channel_x]*pow(p.theta_scale, i0/2.0f);
+        } else {
+            theta_base = data_pos[channel_x + ne2 * 3]*pow(p.theta_scale, i0/2.0f);
+        }
+    } else {
+        if (sector < p.sections[0]) {
+            theta_base = data_pos[channel_x]*pow(p.theta_scale, i0/2.0f);
+        }
+        else if (sector >= p.sections[0] && sector < sec_w) {
+            theta_base = data_pos[channel_x + ne2 * 1]*pow(p.theta_scale, i0/2.0f);
+        }
+        else if (sector >= sec_w && sector < sec_w + p.sections[2]) {
+            theta_base = data_pos[channel_x + ne2 * 2]*pow(p.theta_scale, i0/2.0f);
+        }
+        else if (sector >= sec_w + p.sections[2]) {
+            theta_base = data_pos[channel_x + ne2 * 3]*pow(p.theta_scale, i0/2.0f);
+        }
     }
 
     const float freq_factor = p.has_ff != 0 ? data_ff[i0/2] : 1.0f;