ggml/src
2025-07-01 11:52:14 +03:00
..
ggml-blas cmake : Fix broken CMake error messages (#1252) 2025-05-31 13:39:19 +03:00
ggml-cann CANN: Simplify the environment variable setting(#13104) 2025-06-10 09:59:25 +03:00
ggml-cpu ggml-cpu : "align corners" for bilinear upscale/downscale (#1285) 2025-07-01 09:11:00 +02:00
ggml-cuda HIP: enable vec fattn on RDNA4 (llama/14323) 2025-07-01 11:52:14 +03:00
ggml-hip HIP: disable rocwmma on gfx12 by default until rocm 7.0 (llama/14202) 2025-06-18 10:21:15 +03:00
ggml-kompute llama : add Qwen2VL support + multimodal RoPE (llama/10361) 2024-12-17 19:23:40 +02:00
ggml-metal metal : fix thread-safety (llama/14300) 2025-07-01 11:52:14 +03:00
ggml-musa musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy (llama/13647) 2025-05-25 10:46:24 +03:00
ggml-opencl opencl: add mul_mv_id_q4_0_f32_8x_flat (llama/14003) 2025-06-18 10:21:15 +03:00
ggml-rpc rpc : nicer error messages for RPC server crash (llama/14076) 2025-06-18 10:21:15 +03:00
ggml-sycl sycl: add usage of enqueue_functions extension (llama/14244) 2025-06-20 21:14:52 +03:00
ggml-vulkan Add support for VK_EXT_debug_utils to add labels to Vulkan objects. (llama/13792) 2025-07-01 11:52:14 +03:00
CMakeLists.txt Implement GGML_CPU_ALL_VARIANTS for PowerPC (llama/14286) 2025-06-20 21:14:52 +03:00
ggml-alloc.c ggml: Don't assert fail when tensor data changes (llama/13222) 2025-05-02 21:18:08 +03:00
ggml-backend-impl.h ggml : upgrade init_tensor API to return a ggml_status (llama/11854) 2025-03-04 21:24:42 +02:00
ggml-backend-reg.cpp build : suppress gcc15 compile warnings (llama/14261) 2025-06-20 21:14:52 +03:00
ggml-backend.cpp sched : avoid changing cur_copy when a graph is already allocated (llama/13922) 2025-06-01 14:01:05 +03:00
ggml-common.h ggml-cpu : split arch-specific implementations (llama/13892) 2025-06-10 09:59:25 +03:00
ggml-impl.h ggml : Print backtrace on uncaught C++ exceptions (#1232) 2025-05-28 02:58:46 +02:00
ggml-opt.cpp mnist: fix segmentation fault (#1227) 2025-05-19 09:33:35 +02:00
ggml-quants.c ggml-quants : rename best_mad to best_error (#1283) 2025-06-24 06:10:16 +02:00
ggml-quants.h ggml : build backends as libraries (llama/10256) 2024-11-15 22:51:53 +02:00
ggml-threading.cpp ggml : build backends as libraries (llama/10256) 2024-11-15 22:51:53 +02:00
ggml-threading.h remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797) 2024-12-17 19:23:40 +02:00
ggml.c ggml-cpu : "align corners" for bilinear upscale/downscale (#1285) 2025-07-01 09:11:00 +02:00
ggml.cpp ggml : Print backtrace on uncaught C++ exceptions (#1232) 2025-05-28 02:58:46 +02:00
gguf.cpp gguf: fix failure on version == 0 (llama/13956) 2025-06-10 09:59:25 +03:00