Commit ac02174
authored
fix(docker): Fix GGML_CUDA param (abetlen#1633)
1 parent 8297a0d commit ac02174
1 file changed
Lines changed: 2 additions & 2 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
@@ -15,13 +15,13 @@ COPY . . | |||
| 15 | 15 | ||
| 16 | 16 | # setting build related env vars | |
| 17 | 17 | ENV CUDA_DOCKER_ARCH=all | |
| 18 | - ENV LLAMA_CUBLAS=1 | ||
| 18 | + ENV GGML_CUDA=1 | ||
| 19 | 19 | ||
| 20 | 20 | # Install depencencies | |
| 21 | 21 | RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings starlette-context | |
| 22 | 22 | ||
| 23 | 23 | # Install llama-cpp-python (build with cuda) | |
| 24 | - RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python | ||
| 24 | + RUN CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python | ||
| 25 | 25 | ||
| 26 | 26 | # Run the server | |
| 27 | 27 | CMD python3 -m llama_cpp.server | |
0 commit comments