add fast mat-vec kernels for i-quants (#22344)

2026-04-27 08:25:45 -07:00
parent 4414c04b9a
commit 665abc6097
3 changed files with 543 additions and 0 deletions
@@ -1391,6 +1391,17 @@ static webgpu_encoded_op ggml_webgpu_mul_mat(webgpu_context & ctx,
                case GGML_TYPE_Q2_K:
                    use_fast = true;
                    break;
+                case GGML_TYPE_IQ1_S:
+                case GGML_TYPE_IQ1_M:
+                case GGML_TYPE_IQ2_XXS:
+                case GGML_TYPE_IQ2_XS:
+                case GGML_TYPE_IQ2_S:
+                case GGML_TYPE_IQ3_XXS:
+                case GGML_TYPE_IQ3_S:
+                case GGML_TYPE_IQ4_NL:
+                case GGML_TYPE_IQ4_XS:
+                    use_fast = is_vec;
+                    break;
                default:
                    break;
            }