Skip to content

GitLab

Unverified Commit 3a1ed9ff authored by Jeffrey Morgan's avatar Jeffrey Morgan Committed by GitHub
Browse files

restore building runner with `AVX` on by default (#900)

parent 6d283882
Hide whitespace changes
Inline Side-by-side
Showing with 3 additions and 3 deletions
llm/llama.cpp/generate_linux.go
View file @ 3a1ed9ff
...@@ -14,13 +14,13 @@ package llm ...@@ -14,13 +14,13 @@ package llm
//go:generate git submodule update --force gguf //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-copy-cuda-runtime-libraries.patch
//go:generate git -C gguf apply ../patches/0001-update-default-log-target.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 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 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 -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 --build ggml/build/cuda --target server --config Release
//go:generate mv ggml/build/cuda/bin/server ggml/build/cuda/bin/ollama-runner //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 cmake --build gguf/build/cuda --target server --config Release
//go:generate mv gguf/build/cuda/bin/server gguf/build/cuda/bin/ollama-runner //go:generate mv gguf/build/cuda/bin/server gguf/build/cuda/bin/ollama-runner
llm/llama.cpp/generate_windows.go
View file @ 3a1ed9ff
...@@ -11,6 +11,6 @@ package llm ...@@ -11,6 +11,6 @@ package llm
//go:generate git submodule update --force gguf //go:generate git submodule update --force gguf
//go:generate git -C gguf apply ../patches/0001-update-default-log-target.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 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 //go:generate cmd /c move gguf\build\cpu\bin\Release\server.exe gguf\build\cpu\bin\Release\ollama-runner.exe
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment