vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Refactor: Removes code permanently excluded from compilation to increase readability.

Browse source
This commit is contained in:
Andreas Kieslinger 2025-01-09 12:44:14 +00:00
parent 0cdc133919
commit dd95edfcfb
1 changed files with 1 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

13
ggml/src/ggml-cuda/ggml-cuda.cu
View file

@ -2543,19 +2543,8 @@ static void evaluate_and_capture_cuda_graph(ggml_backend_cuda_context * cuda_ctx
CUDA_CHECK(cudaGraphDestroy(cuda_ctx->cuda_graph->graph));
cuda_ctx->cuda_graph->graph = nullptr;
}
CUDA_CHECK(cudaStreamEndCapture(cuda_ctx->stream(), &cuda_ctx->cuda_graph->graph));
#if 0
if (disable_cuda_graphs_due_to_failed_capture) {
use_cuda_graph = false;
cuda_ctx->cuda_graph->disable_due_to_failed_graph_capture = true;
#ifndef NDEBUG
GGML_LOG_DEBUG("%s: disabling CUDA graphs due to failed graph capture\n", __func__);
#endif
} else {
graph_evaluated_or_captured = true; // CUDA graph has been captured
}
#endif
CUDA_CHECK(cudaStreamEndCapture(cuda_ctx->stream(), &cuda_ctx->cuda_graph->graph));
graph_evaluated_or_captured = true; // CUDA graph has been captured
} else {
graph_evaluated_or_captured = true; // ggml graph has been directly evaluated