Johannes Gäßler b1f3a6e5db llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653) пре 1 месец
..
ggml-alloc.h b1f3a6e5db llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653) пре 1 месец
ggml-backend.h b1f3a6e5db llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653) пре 1 месец
ggml-blas.h ae8de6d50a ggml : build backends as libraries (#10256) пре 1 година
ggml-cann.h ae8de6d50a ggml : build backends as libraries (#10256) пре 1 година
ggml-cpp.h 4254bb4951 ggml : fix ggml_gallocr_ptr type (ggml/1205) пре 8 месеци
ggml-cpu.h 51604435e8 ggml-cpu : fix RISC-V Q4_0 repack select and RVV feature reporting (#17951) пре 1 месец
ggml-cuda.h ae8de6d50a ggml : build backends as libraries (#10256) пре 1 година
ggml-hexagon.h 63d2fc46e1 Add experimental ggml-hexagon backend for the Hexagon NPU (#16547) пре 2 месеци
ggml-metal.h 0320ac5264 metal : refactor + optimize v2 (#15995) пре 4 месеци
ggml-opencl.h a76c56fa1a Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693) пре 1 година
ggml-opt.h 5cdb27e091 finetune: SGD optimizer, more CLI args (#13873) пре 5 месеци
ggml-rpc.h 8160b38a5f rpc : fix alloc size logic (#17116) пре 1 месец
ggml-sycl.h ae8de6d50a ggml : build backends as libraries (#10256) пре 1 година
ggml-vulkan.h c2a67efe38 vulkan: Make Vulkan optional at runtime (#11493). (#11494) пре 11 месеци
ggml-webgpu.h 21c021745d ggml: Add initial WebGPU backend (#14521) пре 6 месеци
ggml-zdnn.h 264f1b5187 zdnn: refactor codebase + add docs (#16178) пре 3 месеци
ggml-zendnn.h 017761daf5 ggml-zendnn : add ZenDNN backend for AMD CPUs (#17690) пре 1 месец
ggml.h b1f3a6e5db llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653) пре 1 месец
gguf.h 53ff6b9b9f GGUF: C++ refactor, backend support, misc fixes (#11030) пре 1 година