f221637053
* linux gpu support * handle multiple gpus * add cuda docker image (#488) --------- Co-authored-by: Michael Yang <mxyng@pm.me>
17 lines
657 B
Go
17 lines
657 B
Go
//go:build !darwin
|
|
// +build !darwin
|
|
|
|
package llm
|
|
|
|
//go:generate git submodule init
|
|
|
|
//go:generate git submodule update --force ggml
|
|
//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/cpu -DLLAMA_K_QUANTS=on
|
|
//go:generate cmake --build ggml/build/cpu --target server --config Release
|
|
|
|
//go:generate git submodule update --force gguf
|
|
//go:generate cmake -S gguf -B gguf/build/cpu -DLLAMA_K_QUANTS=on
|
|
//go:generate cmake --build gguf/build/cpu --target server --config Release
|