LLM inference in C/C++
C++ ggml
docs: added a note about using OpenCl with Adreno 810 (#25786)
akleineac2557cb24de
diff --git a/docs/backend/OPENCL.md b/docs/backend/OPENCL.mdindex 1bce56cd85..76f56bb106 100644--- a/docs/backend/OPENCL.md+++ b/docs/backend/OPENCL.md@@ -47,6 +47,7 @@ The llama.cpp OpenCL backend is designed to enable llama.cpp on **Qualcomm Adren| Adreno GPU | Status ||:-------------------------------------:|:-------:|| Adreno 750 (Snapdragon 8 Gen 3) | Support |+| Adreno 810 (Snapdragon 7s Gen 3) | Support || Adreno 830 (Snapdragon 8 Elite) | Support || Adreno 840 (Snapdragon 8 Elite Gen 5) | Support || Adreno X1-85 (Snapdragon X Elite) | Support |diff --git a/ggml/src/ggml-opencl/ggml-opencl.cpp b/ggml/src/ggml-opencl/ggml-opencl.cppindex 2a7411c019..b8e7a5614e 100644--- a/ggml/src/ggml-opencl/ggml-opencl.cpp+++ b/ggml/src/ggml-opencl/ggml-opencl.cpp@@ -264,7 +264,8 @@ static ADRENO_GPU_GEN get_adreno_gpu_gen(const char *device_name) {return ADRENO_GPU_GEN::A7X;}- if (strstr(device_name, "830") ||+ if (strstr(device_name, "810") ||+ strstr(device_name, "830") ||strstr(device_name, "840") ||strstr(device_name, "850")) {return ADRENO_GPU_GEN::A8X;