AI/turbopilot
1
0
Fork 0
mirror of https://github.com/ravenscroftj/turbopilot.git synced 2024-10-01 01:06:01 -04:00
Code Issues Packages Projects Releases Wiki Activity

update build instructions

Browse Source
This commit is contained in:
James Ravenscroft 2023-08-05 09:22:15 +01:00
parent 57ab06d457
commit 7266451f44
1 changed files with 4 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
BUILD.md
View File

@ -32,25 +32,19 @@ Make sure the ggml subproject is checked out with `git submodule init` and `git
Configure cmake to build the project with the following: Configure cmake to build the project with the following:
```bash ```bash
mkdir ggml/build mkdir build
cd ggml/build cd build
cmake .. cmake ..
``` ```
If you are running on linux you can optionally compile a static build with `cmake -D CMAKE_EXE_LINKER_FLAGS="-static" ..` which should make your binary portable across different flavours of the OS. If you are running on linux you can optionally compile a static build with `cmake -D CMAKE_EXE_LINKER_FLAGS="-static" ..` which should make your binary portable across different flavours of the OS.
From here you can now build the components that make up turbopilot: From here you can now build the components that make up turbopilot by running:
```bash ```bash
make codegen codegen-quantize codegen-serve make
``` ```
Where:
- *codegen* is a command line tool for testing out prompts in a lightweight way (a lot like llama.cpp)
- *codegen-serve* is the actual REST server that can be used to connect to VSCode
- *codegen-quantize* is the tool for quantizing models exported by the conversion script. For more details see [Converting and Quantizing The Models](https://github.com/ravenscroftj/turbopilot/wiki/Converting-and-Quantizing-The-Models).
### Building with OpenBLAS ### Building with OpenBLAS