highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-10-11 12:13:27 +02:00
Code Issues Packages Projects Releases Wiki Activity

windows CUDA support (#1262)

Browse Source 
* Support cuda build in Windows
* Enable dynamic NumGPU allocation for Windows
This commit is contained in:
Jing Zhang
2023-11-24 14:16:36 -08:00
committed by GitHub
parent 12e8c12d2b
commit 82b9b329ff
3 changed files with 11 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
llm/llama.cpp/generate_windows.go
View File

@@ -14,3 +14,11 @@ package llm
//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