ollama/llm/llama.cpp/generate.go

//go:build !darwin
// +build !darwin

package llm

//go:generate git submodule init
//go:generate git submodule update --force ggml gguf
//go:generate git -C ggml apply ../ggml_patch/0001-add-detokenize-endpoint.patch
//go:generate git -C ggml apply ../ggml_patch/0002-34B-model-support.patch
//go:generate git -C ggml apply ../ggml_patch/0003-metal-fix-synchronization-in-new-matrix-multiplicati.patch
//go:generate git -C ggml apply ../ggml_patch/0004-metal-add-missing-barriers-for-mul-mat-2699.patch
//go:generate cmake --fresh -S ggml -B ggml/build/cpu -DLLAMA_K_QUANTS=on
//go:generate cmake --build ggml/build/cpu --target server --config Release
//go:generate cmake -S gguf -B gguf/build/cpu -DLLAMA_K_QUANTS=on
//go:generate cmake --build gguf/build/cpu --target server --config Release
generate binary dependencies based on GOARCH on macos (#459) 2023-09-05 16:53:57 +00:00			`//go:build !darwin`
			`// +build !darwin`

subprocess llama.cpp server (#401) * remove c code * pack llama.cpp * use request context for llama_cpp * let llama_cpp decide the number of threads to use * stop llama runner when app stops * remove sample count and duration metrics * use go generate to get libraries * tmp dir for running llm 2023-08-30 20:35:03 +00:00			`package llm`

			`//go:generate git submodule init`
GGUF support (#441) 2023-09-07 17:55:37 +00:00			`//go:generate git submodule update --force ggml gguf`
subprocess llama.cpp server (#401) * remove c code * pack llama.cpp * use request context for llama_cpp * let llama_cpp decide the number of threads to use * stop llama runner when app stops * remove sample count and duration metrics * use go generate to get libraries * tmp dir for running llm 2023-08-30 20:35:03 +00:00			`//go:generate git -C ggml apply ../ggml_patch/0001-add-detokenize-endpoint.patch`
			`//go:generate git -C ggml apply ../ggml_patch/0002-34B-model-support.patch`
metal: add missing barriers for mul-mat (#469) 2023-09-05 23:37:13 +00:00			`//go:generate git -C ggml apply ../ggml_patch/0003-metal-fix-synchronization-in-new-matrix-multiplicati.patch`
			`//go:generate git -C ggml apply ../ggml_patch/0004-metal-add-missing-barriers-for-mul-mat-2699.patch`
			`//go:generate cmake --fresh -S ggml -B ggml/build/cpu -DLLAMA_K_QUANTS=on`
subprocess llama.cpp server (#401) * remove c code * pack llama.cpp * use request context for llama_cpp * let llama_cpp decide the number of threads to use * stop llama runner when app stops * remove sample count and duration metrics * use go generate to get libraries * tmp dir for running llm 2023-08-30 20:35:03 +00:00			`//go:generate cmake --build ggml/build/cpu --target server --config Release`
GGUF support (#441) 2023-09-07 17:55:37 +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`