EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

devops : remove clblast + LLAMA_CUDA -> GGML_CUDA (#8139)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2024-06-26 19:32:07 +03:00
committed by GitHub
parent a95631ee97
commit 0e814dfc42
12 changed files with 19 additions and 103 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.devops/llama-cli-rocm.Dockerfile
View File

@@ -36,7 +36,7 @@ COPY . .
# Set nvcc architecture
ENV GPU_TARGETS=${ROCM_DOCKER_ARCH}
# Enable ROCm
ENV LLAMA_HIPBLAS=1
ENV GGML_HIPBLAS=1
ENV CC=/opt/rocm/llvm/bin/clang
ENV CXX=/opt/rocm/llvm/bin/clang++