From f4dea7da1841a92d2788b0535063abf2f0e28461 Mon Sep 17 00:00:00 2001 From: Shijie <821898965@qq.com> Date: Tue, 16 Apr 2024 23:40:48 +0800 Subject: llama : add qwen2moe (#6074) * support qwen2moe * fix-review * metal : support unary ops for nelements % 4 != 0 * metal : require contiguousness for float4 unary kernels * metal : require contiguousness for float4 unary kernels (cont) * fix-review * names : for brevity "SHARED_EXP" -> "SHEXP" * llama : reuse build_moe_ffn() * llama : add model type name --------- Co-authored-by: Georgi Gerganov --- tests/test-backend-ops.cpp | 1 + 1 file changed, 1 insertion(+) (limited to 'tests') diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp index b5067595..21adba42 100644 --- a/tests/test-backend-ops.cpp +++ b/tests/test-backend-ops.cpp @@ -1878,6 +1878,7 @@ static bool test_backend(ggml_backend_t backend, test_mode mode, const char * op // unary ops for (int op = 0; op < GGML_UNARY_OP_COUNT; op++) { test_cases.emplace_back(new test_unary((ggml_unary_op) op)); + test_cases.emplace_back(new test_unary((ggml_unary_op) op, GGML_TYPE_F32, { 7, 13, 19, 23 })); } test_cases.emplace_back(new test_get_rows(GGML_TYPE_F32, 1, 8, 2, 1, false)); -- cgit v1.2.3