RubyGems - llama_cpp - Versions diffs - 0.13.0 → 0.14.1 - Mend

llama_cpp 0.13.0 → 0.14.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (32) hide show

checksums.yaml +4 -4
data/CHANGELOG.md +20 -0
data/ext/llama_cpp/llama_cpp.cpp +130 -26
data/lib/llama_cpp/version.rb +2 -2
data/sig/llama_cpp.rbs +15 -4
data/vendor/tmp/llama.cpp/Makefile +30 -15
data/vendor/tmp/llama.cpp/ggml-alloc.c +45 -64
data/vendor/tmp/llama.cpp/ggml-alloc.h +13 -5
data/vendor/tmp/llama.cpp/ggml-backend-impl.h +17 -5
data/vendor/tmp/llama.cpp/ggml-backend.c +371 -151
data/vendor/tmp/llama.cpp/ggml-backend.h +54 -29
data/vendor/tmp/llama.cpp/ggml-common.h +1830 -0
data/vendor/tmp/llama.cpp/ggml-cuda.cu +765 -830
data/vendor/tmp/llama.cpp/ggml-impl.h +6 -2
data/vendor/tmp/llama.cpp/ggml-kompute.cpp +7 -2
data/vendor/tmp/llama.cpp/ggml-metal.m +105 -27
data/vendor/tmp/llama.cpp/ggml-metal.metal +99 -920
data/vendor/tmp/llama.cpp/ggml-opencl.cpp +2 -2
data/vendor/tmp/llama.cpp/ggml-quants.c +557 -1129
data/vendor/tmp/llama.cpp/ggml-quants.h +27 -259
data/vendor/tmp/llama.cpp/ggml-sycl.cpp +3332 -1195
data/vendor/tmp/llama.cpp/ggml-sycl.h +5 -0
data/vendor/tmp/llama.cpp/ggml-vulkan-shaders.hpp +39336 -43461
data/vendor/tmp/llama.cpp/ggml-vulkan.cpp +1302 -781
data/vendor/tmp/llama.cpp/ggml-vulkan.h +1 -0
data/vendor/tmp/llama.cpp/ggml.c +734 -356
data/vendor/tmp/llama.cpp/ggml.h +91 -51
data/vendor/tmp/llama.cpp/llama.cpp +1938 -759
data/vendor/tmp/llama.cpp/llama.h +53 -21
data/vendor/tmp/llama.cpp/unicode.cpp +1672 -0
data/vendor/tmp/llama.cpp/unicode.h +16 -774
metadata +4 -2

data/vendor/tmp/llama.cpp/ggml-opencl.cpp CHANGED Viewed

@@ -2231,7 +2231,7 @@ static ggml_backend_buffer_type_t ggml_backend_opencl_get_default_buffer_type(gg
     GGML_UNUSED(backend);
 }
-static bool ggml_backend_opencl_graph_compute(ggml_backend_t backend, ggml_cgraph * graph) {
+static ggml_status ggml_backend_opencl_graph_compute(ggml_backend_t backend, ggml_cgraph * graph) {
     for (int i = 0; i < graph->n_nodes; ++i) {
         ggml_tensor * node = graph->nodes[i];
         switch (node->op) {
@@ -2246,7 +2246,7 @@ static bool ggml_backend_opencl_graph_compute(ggml_backend_t backend, ggml_cgrap
         }
     }
-    return true;
+    return GGML_STATUS_SUCCESS;
     GGML_UNUSED(backend);
 }