ggml-org/llama.cpp b11592

on GitHub

cuda : add GGML_CUDA_GRAPH_DEBUG and read env vars once (#30327)

• ggml-cuda: gate CUDA graph debug logs behind GGML_CUDA_GRAPH_DEBUG

• ggml-cuda: cache env var lookups in static const instead of re-reading per call

• ggml-cuda: read env vars exactly once via ggml_cuda_env_flag/ggml_cuda_env_int

• ggml-cuda: consolidate env flag reads into single static accessors

• ggml-cuda : drop env helper comments

Assisted-by: pi:llama.cpp/Qwen3.8-27B

• cont : remove NDEBUG gates for CUDA graph logs