mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-13 03:16:47 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

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

13
llm/llama.cpp/generate_linux.go
View file

@ -1,14 +1,3 @@
package llm
//go:generate git submodule init
//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 -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 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
//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 sh ./gen_linux.sh