2023-09-12 23:04:35 +08:00
|
|
|
package llm
|
|
|
|
|
|
|
|
|
|
//go:generate git submodule init
|
|
|
|
|
|
|
|
|
|
//go:generate git submodule update --force gguf
|
2023-09-21 03:15:23 +08:00
|
|
|
//go:generate git -C gguf apply ../patches/0001-copy-cuda-runtime-libraries.patch
|
2023-10-24 01:41:18 +08:00
|
|
|
//go:generate git -C gguf apply ../patches/0001-update-default-log-target.patch
|
2023-10-28 03:13:44 +08:00
|
|
|
//go:generate cmake -S gguf -B gguf/build/cpu -DLLAMA_K_QUANTS=on -DLLAMA_NATIVE=off -DLLAMA_AVX=on -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off
|
2023-09-15 03:08:13 +08:00
|
|
|
//go:generate cmake --build gguf/build/cpu --target server --config Release
|
2023-10-06 22:15:42 +08:00
|
|
|
//go:generate mv gguf/build/cpu/bin/server gguf/build/cpu/bin/ollama-runner
|
2023-09-15 03:08:13 +08:00
|
|
|
|
2023-11-25 03:05:57 +08:00
|
|
|
//go:generate cmake -S gguf -B gguf/build/cuda -DLLAMA_CUBLAS=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on -DLLAMA_NATIVE=off -DLLAMA_AVX=on -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off -DLLAMA_CUDA_PEER_MAX_BATCH_SIZE=0
|
2023-09-21 03:00:41 +08:00
|
|
|
//go:generate cmake --build gguf/build/cuda --target server --config Release
|
2023-10-06 22:15:42 +08:00
|
|
|
//go:generate mv gguf/build/cuda/bin/server gguf/build/cuda/bin/ollama-runner
|
