matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-11 16:26:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add cgo implementation for llama.cpp

Browse Source 
Run the server.cpp directly inside the Go runtime via cgo
while retaining the LLM Go abstractions.
This commit is contained in:
Daniel Hiltgen
2023-11-13 17:20:34 -08:00
parent 5e7fd6906f
commit d4cd695759
27 changed files with 1189 additions and 765 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
llm/llama.cpp/generate_windows.go
View File

@@ -1,17 +1,3 @@
package llm
//go:generate git submodule init
//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 -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
//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 cmd /c move ggml\build\cuda\bin\Release\server.exe ggml\build\cuda\bin\Release\ollama-runner.exe
//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 cmd /c move gguf\build\cuda\bin\Release\server.exe gguf\build\cuda\bin\Release\ollama-runner.exe
//go:generate powershell -ExecutionPolicy Bypass -File ./gen_windows.ps1