Commit History

Author SHA1 Message Date
  Diego Devesa 5931c1f233 ggml : add support for dynamic loading of backends (#10469) 1 year ago
  haopeng 42ae10bbcd add cmake rvv support (#10411) 1 year ago
  bandoti 2a11b6b094 Add required ggml-base and backend libs to cmake pkg (#10407) 1 year ago
  Romain Biessy 2a1507c162 sycl : Add option to set the SYCL architecture for all targets (#10266) 1 year ago
  Johannes Gäßler c3ea58aca4 CUDA: remove DMMV, consolidate F16 mult mat vec (#10318) 1 year ago
  Johannes Gäßler 8a43e940ab ggml: new optimization interface (ggml/988) 1 year ago
  Charles Xu 1607a5e5b0 backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (#9921) 1 year ago
  Diego Devesa ae8de6d50a ggml : build backends as libraries (#10256) 1 year ago
  Georgi Gerganov ec450d3bbf metal : opt-in compile flag for BF16 (#10218) 1 year ago
  Diego Devesa 97404c4a03 ggml : add ggml-cpu.h to the public headers (#10204) 1 year ago
  Ma Mingfei 60ce97c9d8 add amx kernel for gemm (#8998) 1 year ago
  Georgi Gerganov 19514d632e cmake : do not hide GGML options + rename option (#9465) 1 year ago
  Markus Tavenrath 8ebe8ddebd Improve Vulkan shader build system (#9239) 1 year ago
  0cc4m 5fd89a70ea Vulkan Optimizations and Fixes (#8959) 1 year ago
  Georgi Gerganov 43bdd3ce18 cmake : remove unused option GGML_CURL (#9011) 1 year ago
  wangshuai09 6e2b6000e5 cann: update cmake (#8765) 1 year ago
  R0CKSTAR e54c35e4fb feat: Support Moore Threads GPU (#8383) 1 year ago
  Borislav Stanimirov d2b851bfa1 cmake : only enable GGML_NATIVE and x86 flags if not crosscompiling (ggml/885) 1 year ago
  65a 705b7ecf60 cmake : install all ggml public headers (#8480) 1 year ago
  Georgi Gerganov 6b2a849d1f ggml : move sgemm sources to llamafile subfolder (#8394) 1 year ago
  slaren 31ec3993f6 ggml : add GGML_CUDA_USE_GRAPHS option, restore GGML_CUDA_FORCE_CUBLAS (cmake) (#8140) 1 year ago
  Georgi Gerganov f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 year ago