highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-08-09 02:42:52 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix ggml arm64 cuda build (#520)

Browse Source
This commit is contained in:
Bruce MacDonald
2023-09-12 17:06:48 -04:00
committed by GitHub
parent f221637053
commit f59c4d03f7
2 changed files with 35 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
llm/llama.cpp/generate_linux.go
View File

@@ -6,9 +6,10 @@ package llm
//go:generate -command git-apply git -C ggml apply
//go:generate git-apply ../ggml_patch/0001-add-detokenize-endpoint.patch
//go:generate git-apply ../ggml_patch/0002-34B-model-support.patch
//go:generate cmake -S ggml -B ggml/build/gpu -DLLAMA_CUBLAS=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on
//go:generate git-apply ../ggml_patch/0005-ggml-support-CUDA-s-half-type-for-aarch64-1455-2670.patch
//go:generate cmake -S ggml -B ggml/build/gpu -DLLAMA_CUBLAS=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on
//go:generate cmake --build ggml/build/gpu --target server --config Release
//go:generate git submodule update --force gguf
//go:generate cmake -S gguf -B gguf/build/gpu -DLLAMA_CUBLAS=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on
//go:generate cmake -S gguf -B gguf/build/gpu -DLLAMA_CUBLAS=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on
//go:generate cmake --build gguf/build/gpu --target server --config Release