ollama/llm/llama.cpp/ggml_patch
2023-09-12 17:06:48 -04:00
..
0001-add-detokenize-endpoint.patch subprocess llama.cpp server (#401) 2023-08-30 16:35:03 -04:00
0002-34B-model-support.patch subprocess llama.cpp server (#401) 2023-08-30 16:35:03 -04:00
0003-metal-add-missing-barriers-for-mul-mat-2699.patch metal: add missing barriers for mul-mat (#469) 2023-09-05 19:37:13 -04:00
0003-metal-fix-synchronization-in-new-matrix-multiplicati.patch metal: add missing barriers for mul-mat (#469) 2023-09-05 19:37:13 -04:00
0004-metal-add-missing-barriers-for-mul-mat-2699.patch metal: add missing barriers for mul-mat (#469) 2023-09-05 19:37:13 -04:00
0005-ggml-support-CUDA-s-half-type-for-aarch64-1455-2670.patch fix ggml arm64 cuda build (#520) 2023-09-12 17:06:48 -04:00