2023-09-12 15:04:35 +00:00
|
|
|
package llm
|
|
|
|
|
|
|
|
|
|
//go:generate git submodule init
|
|
|
|
|
|
|
|
|
|
//go:generate git submodule update --force ggml
|
2023-09-20 19:15:23 +00:00
|
|
|
//go:generate git -C ggml apply ../patches/0001-add-detokenize-endpoint.patch
|
|
|
|
|
//go:generate git -C ggml apply ../patches/0002-34B-model-support.patch
|
|
|
|
|
//go:generate git -C ggml apply ../patches/0005-ggml-support-CUDA-s-half-type-for-aarch64-1455-2670.patch
|
|
|
|
|
//go:generate git -C ggml apply ../patches/0001-copy-cuda-runtime-libraries.patch
|
2023-09-14 19:08:13 +00:00
|
|
|
//go:generate cmake -S ggml -B ggml/build/cpu -DLLAMA_K_QUANTS=on
|
|
|
|
|
//go:generate cmake --build ggml/build/cpu --target server --config Release
|
2023-09-12 15:04:35 +00:00
|
|
|
|
|
|
|
|
//go:generate git submodule update --force gguf
|
2023-09-20 19:15:23 +00:00
|
|
|
//go:generate git -C gguf apply ../patches/0001-copy-cuda-runtime-libraries.patch
|
2023-09-21 21:48:00 +00:00
|
|
|
//go:generate git -C gguf apply ../patches/0001-remove-warm-up-logging.patch
|
2023-09-14 19:08:13 +00:00
|
|
|
//go:generate cmake -S gguf -B gguf/build/cpu -DLLAMA_K_QUANTS=on
|
|
|
|
|
//go:generate cmake --build gguf/build/cpu --target server --config Release
|
|
|
|
|
|
2023-09-20 19:00:41 +00:00
|
|
|
//go:generate cmake -S ggml -B ggml/build/cuda -DLLAMA_CUBLAS=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on
|
|
|
|
|
//go:generate cmake --build ggml/build/cuda --target server --config Release
|
|
|
|
|
//go:generate cmake -S gguf -B gguf/build/cuda -DLLAMA_CUBLAS=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on
|
|
|
|
|
//go:generate cmake --build gguf/build/cuda --target server --config Release
|
