Skip to content

Commit

Permalink
Start of LlamaComponent, load hardcoded model
Browse files Browse the repository at this point in the history
  • Loading branch information
mika314 committed Aug 26, 2023
1 parent 8305d61 commit 3e1f0d5
Show file tree
Hide file tree
Showing 4 changed files with 449 additions and 0 deletions.
15 changes: 15 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
# Llama.cpp Build Parameters

Llama.cpp was built from git hash: `dadbed99e65252d79f81101a392d0d6497b86caa`

With the following build commands:

```
mkdir build
cd build/
cmake .. -DLLAMA_CUBLAS=ON -DLLAMA_CUDA_DMMV_X=64 -DLLAMA_CUDA_MMV_Y=2 -DLLAMA_CUDA_F16=true -DBUILD_SHARED_LIBS=ON
cd ..
cmake --build build --config Release -j --verbose
```

Then the .so file was copied into the `Libraries` directory and all the .h files were copied to the `Includes` directory.
Loading

0 comments on commit 3e1f0d5

Please sign in to comment.