From a7befb3bed8014193faba0bef04aa48a3e8cabfd Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Thu, 5 Feb 2026 13:42:53 +0200 Subject: [PATCH] Change default FA offset to ln(2) (#1235) * Change default FA offset to ln(2) * Also here --- ggml/src/ggml-cuda.cu | 2 +- ggml/src/ggml-cuda/common.cuh | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/ggml/src/ggml-cuda.cu b/ggml/src/ggml-cuda.cu index 8f07eb5f..b8a8ebb6 100644 --- a/ggml/src/ggml-cuda.cu +++ b/ggml/src/ggml-cuda.cu @@ -4536,7 +4536,7 @@ struct cuda_params { int fusion = GGML_CUDA_FUSION; int offload_batch_size = GGML_CUDA_MIN_BATCH_OFFLOAD; int mmq_id_thresh = 32; - float fa_offset = 0; + float fa_offset = 0.6931f; #ifdef USE_CUDA_GRAPH bool use_cuda_graph = true; #else diff --git a/ggml/src/ggml-cuda/common.cuh b/ggml/src/ggml-cuda/common.cuh index f4209197..db67d1cc 100644 --- a/ggml/src/ggml-cuda/common.cuh +++ b/ggml/src/ggml-cuda/common.cuh @@ -853,7 +853,7 @@ struct ggml_backend_cuda_context { int fusion = GGML_CUDA_FUSION; int offload_batch_size = GGML_CUDA_MIN_BATCH_OFFLOAD; int mmq_id_thresh = 32; - float fa_offset = 0.0f; + float fa_offset = 0.6931f; // ln(2) #ifdef USE_CUDA_GRAPH bool use_cuda_graph = true;