mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-27 08:27:30 -05:00
- return early when the graph has no nodes - drop the redundant reset of capture_compute: the decrement at the top of the function already transitions the counter from 0 to -1, so a capture happens exactly once - hint at METAL_CAPTURE_ENABLED=1 in the capture error message - pass capture_compute == 0 (not the raw counter) as use_capture to ggml_metal_op_init, so GPU debug-group markers are only emitted on the captured compute Assisted-by: pi:llama.cpp/Qwen3.8-27B