From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001 From: Michael Yang Date: Thu, 31 Jul 2025 12:31:58 -0700 Subject: [PATCH] cuda: disable graph compat check for OP_ADD --- ggml/src/ggml-cuda/ggml-cuda.cu | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu index bb19b06e..080e7467 100644 --- a/ggml/src/ggml-cuda/ggml-cuda.cu +++ b/ggml/src/ggml-cuda/ggml-cuda.cu @@ -2509,20 +2509,6 @@ static bool check_node_graph_compatibility_and_refresh_copy_ops(ggml_backend_cud #endif } - // workarounds to exclude Gemma3n's `project_per_layer_input` operation from the batch-size heuristic, specific to ollama's implementation of gemma3n - // number of layers is different for per_layer_proj between gemma3n:2b and gemma3n:4b, which is why we don't check that value here - if (node->op == GGML_OP_ADD && node->src[1] && node->src[1]->ne[1] > 1 && !(node->ne[0] == 256 - && node->ne[2] == 1 - && node->ne[3] == 1 - && node->src[0] ? std::string(node->src[0]->name).find(gemma3n_node_name) != std::string::npos : false - && node->src[1] ? node->src[1]->name == gemma3n_per_layer_proj_src1_name : false)) { - // Generally, changes in batch size or context size can cause changes to the grid size of some kernels. - use_cuda_graph = false; -#ifndef NDEBUG - GGML_LOG_INFO("%s: disabling CUDA graphs due to batch size > 1 [%s] [%ld %ld %ld %ld]\n", __func__, node->name, node->ne[0], node->ne[1], node->ne[2], node->ne[3]); -#endif - } - if (node->op == GGML_OP_CPY) { // Store the pointers which are updated for each token, such that these can be sent