Remove some comments

Author: reeselevine

ggml/src/ggml-webgpu/ggml-webgpu.cpp

@@ -248,7 +248,7 @@ struct webgpu_context_struct {
 
     webgpu_pipeline memset_pipeline;
     webgpu_pipeline mul_mat_pipeline[30][2];
-    webgpu_pipeline set_rows_pipeline[1][2];  // dst->type, vectorized (0 for vectorized, 1 for non vectorized)
+    webgpu_pipeline set_rows_pipeline[1][2];  // dst->type, vectorized
     webgpu_pipeline get_rows_pipeline[30];
     webgpu_pipeline get_rows_f32_no_vec_pipeline;
     webgpu_pipeline cpy_pipeline[2][2];          // src type, dst type
@@ -770,7 +770,6 @@ static std::optional<webgpu_command> ggml_webgpu_set_rows(webgpu_context & ctx,
 
     int             vectorized = src->ne[0] % 4 == 0;
     webgpu_pipeline pipeline   = ctx->set_rows_pipeline[0][vectorized];
-    // if not evenly divisble by 4, use the non-vectorized version
     uint32_t        threads;
     if (vectorized) {
         threads = (src->ne[1] * src->ne[2] * src->ne[3]) * (src->ne[0] / 4);

ggml/src/ggml-webgpu/wgsl-shaders/set_rows.tmpl.wgsl

@@ -104,7 +104,6 @@ fn main(@builtin(global_invocation_id) gid: vec3<u32>) {
     let i_dst_row = params.offset_dst + idx_high_val * params.stride_dst1 + i_src2 * params.stride_dst2 + i_src3 * params.stride_dst3;
     let i_src_row = params.offset_src + i_src1 * params.stride_src1 + i_src2 * params.stride_src2 + i_src3 * params.stride_src3;
 
-    // starts at what element of that row?
     let col_idx = (gid.x % elems_per_row);
     dst[i_dst_row/{{VEC_SIZE}} + col_idx] = {{DST_TYPE}}(src[i_src_row/{{VEC_SIZE}} + col_idx]);
 }