From 38566680cdfe982a495562332c25b9227de9cf8d Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Wed, 17 Jan 2024 18:54:56 +0200 Subject: ggml : add IQ2 to test-backend-ops + refactoring (#4990) * ggml : add IQ2 to test-backend-ops + refactoring ggml-ci * cuda : update supports_op for IQ2 ggml-ci * ci : enable LLAMA_CUBLAS=1 for CUDA nodes ggml-ci * cuda : fix out-of-bounds-access in `mul_mat_vec_q` ggml-ci * tests : avoid creating RNGs for each Q tensor ggml-ci * tests : avoid creating RNGs for each tensor ggml-ci --- ggml-backend.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'ggml-backend.c') diff --git a/ggml-backend.c b/ggml-backend.c index 4266250f..ef518dae 100644 --- a/ggml-backend.c +++ b/ggml-backend.c @@ -692,6 +692,8 @@ GGML_CALL static bool ggml_backend_cpu_graph_compute(ggml_backend_t backend, str GGML_CALL static bool ggml_backend_cpu_supports_op(ggml_backend_t backend, const struct ggml_tensor * op) { switch (op->op) { + case GGML_OP_CPY: + return op->type != GGML_TYPE_IQ2_XXS && op->type != GGML_TYPE_IQ2_XS; // missing type_traits.from_float case GGML_OP_MUL_MAT: return op->src[1]->type == GGML_TYPE_F32 || op->src[1]->type == ggml_internal_get_type_traits(op->src[0]->type).vec_dot_type; default: -- cgit v1.2.3