hrx: keep the model weights in the loader's file mapping instead of a device buffer (engine #856) - #304

hrx: keep the model weights in the loader's file mapping instead of a device buffer (engine #856)#304

bong-water-water-bong merged 2 commits into

1bit/hrx-vulkan-patched1bit-MONSTER/llama.cpp:1bit/hrx-vulkan-patchedfrom

1bit/856-model-buffer1bit-MONSTER/llama.cpp:1bit/856-model-bufferCopy head branch name to clipboard