ollama/llm/llama.cpp/patches
2023-10-24 00:32:36 -07:00
..
0001-add-detokenize-endpoint.patch embed libraries using cmake 2023-09-20 14:41:57 -07:00
0001-copy-cuda-runtime-libraries.patch embed libraries using cmake 2023-09-20 14:41:57 -07:00
0001-metal-handle-ggml_scale-for-n-4-0-close-3754.patch fix metal assertion errors 2023-10-24 00:32:36 -07:00
0001-update-default-log-target.patch update default log target 2023-10-23 10:44:50 -07:00
0002-34B-model-support.patch embed libraries using cmake 2023-09-20 14:41:57 -07:00
0003-metal-fix-synchronization-in-new-matrix-multiplicati.patch embed libraries using cmake 2023-09-20 14:41:57 -07:00
0004-metal-add-missing-barriers-for-mul-mat-2699.patch embed libraries using cmake 2023-09-20 14:41:57 -07:00
0005-ggml-support-CUDA-s-half-type-for-aarch64-1455-2670.patch embed libraries using cmake 2023-09-20 14:41:57 -07:00