From 3a1ed9ff707d1ac4d525e9dfb2a6002c4305bc62 Mon Sep 17 00:00:00 2001 From: Jeffrey Morgan Date: Fri, 27 Oct 2023 12:13:44 -0700 Subject: [PATCH] restore building runner with `AVX` on by default (#900) --- llm/llama.cpp/generate_linux.go | 4 ++-- llm/llama.cpp/generate_windows.go | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/llm/llama.cpp/generate_linux.go b/llm/llama.cpp/generate_linux.go index 23920265..2e8264ce 100644 --- a/llm/llama.cpp/generate_linux.go +++ b/llm/llama.cpp/generate_linux.go @@ -14,13 +14,13 @@ package llm //go:generate git submodule update --force gguf //go:generate git -C gguf apply ../patches/0001-copy-cuda-runtime-libraries.patch //go:generate git -C gguf apply ../patches/0001-update-default-log-target.patch -//go:generate cmake -S gguf -B gguf/build/cpu -DLLAMA_K_QUANTS=on +//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 //go:generate cmake --build gguf/build/cpu --target server --config Release //go:generate mv gguf/build/cpu/bin/server gguf/build/cpu/bin/ollama-runner //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 mv ggml/build/cuda/bin/server ggml/build/cuda/bin/ollama-runner -//go:generate cmake -S gguf -B gguf/build/cuda -DLLAMA_CUBLAS=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on +//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 //go:generate cmake --build gguf/build/cuda --target server --config Release //go:generate mv gguf/build/cuda/bin/server gguf/build/cuda/bin/ollama-runner diff --git a/llm/llama.cpp/generate_windows.go b/llm/llama.cpp/generate_windows.go index 3db1a3e0..326e83d5 100644 --- a/llm/llama.cpp/generate_windows.go +++ b/llm/llama.cpp/generate_windows.go @@ -11,6 +11,6 @@ package llm //go:generate git submodule update --force gguf //go:generate git -C gguf apply ../patches/0001-update-default-log-target.patch -//go:generate cmake -S gguf -B gguf/build/cpu -DLLAMA_K_QUANTS=on +//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 //go:generate cmake --build gguf/build/cpu --target server --config Release //go:generate cmd /c move gguf\build\cpu\bin\Release\server.exe gguf\build\cpu\bin\Release\ollama-runner.exe