rename Dockerfiles

ggerganov · Jun 8, 2024 · 347f308 · 347f308
1 parent 78eae7f
commit 347f308
Show file tree

Hide file tree

Showing 13 changed files with 13 additions and 13 deletions.
diff --git a/.devops/main-cuda.Dockerfile → .devops/llama-cuda.Dockerfile b/.devops/main-cuda.Dockerfile → .devops/llama-cuda.Dockerfile
diff --git a/.devops/main-intel.Dockerfile → .devops/llama-intel.Dockerfile b/.devops/main-intel.Dockerfile → .devops/llama-intel.Dockerfile
diff --git a/.devops/main-rocm.Dockerfile → .devops/llama-rocm.Dockerfile b/.devops/main-rocm.Dockerfile → .devops/llama-rocm.Dockerfile
diff --git a/.devops/server-cuda.Dockerfile → .devops/llama-server-cuda.Dockerfile b/.devops/server-cuda.Dockerfile → .devops/llama-server-cuda.Dockerfile
diff --git a/.devops/server-intel.Dockerfile → .devops/llama-server-intel.Dockerfile b/.devops/server-intel.Dockerfile → .devops/llama-server-intel.Dockerfile
diff --git a/.devops/server-rocm.Dockerfile → .devops/llama-server-rocm.Dockerfile b/.devops/server-rocm.Dockerfile → .devops/llama-server-rocm.Dockerfile
diff --git a/.devops/server-vulkan.Dockerfile → .devops/llama-server-vulkan.Dockerfile b/.devops/server-vulkan.Dockerfile → .devops/llama-server-vulkan.Dockerfile
diff --git a/.devops/server.Dockerfile → .devops/llama-server.Dockerfile b/.devops/server.Dockerfile → .devops/llama-server.Dockerfile
diff --git a/.devops/main-vulkan.Dockerfile → .devops/llama-vulkan.Dockerfile b/.devops/main-vulkan.Dockerfile → .devops/llama-vulkan.Dockerfile
diff --git a/.devops/main.Dockerfile → .devops/llama.Dockerfile b/.devops/main.Dockerfile → .devops/llama.Dockerfile
diff --git a/.github/workflows/docker.yml b/.github/workflows/docker.yml
@@ -30,20 +30,20 @@ jobs:
  strategy:
  matrix:
  config:
- - { tag: "light", dockerfile: ".devops/main.Dockerfile", platforms: "linux/amd64,linux/arm64" }
+ - { tag: "light", dockerfile: ".devops/llama.Dockerfile", platforms: "linux/amd64,linux/arm64" }
  - { tag: "full", dockerfile: ".devops/full.Dockerfile", platforms: "linux/amd64,linux/arm64" }
- - { tag: "server", dockerfile: ".devops/server.Dockerfile", platforms: "linux/amd64,linux/arm64" }
+ - { tag: "server", dockerfile: ".devops/llama-server.Dockerfile", platforms: "linux/amd64,linux/arm64" }
  # NOTE(canardletter): The CUDA builds on arm64 are very slow, so I
  # have disabled them for now until the reason why
  # is understood.
- - { tag: "light-cuda", dockerfile: ".devops/main-cuda.Dockerfile", platforms: "linux/amd64" }
+ - { tag: "light-cuda", dockerfile: ".devops/llama-cuda.Dockerfile", platforms: "linux/amd64" }
  - { tag: "full-cuda", dockerfile: ".devops/full-cuda.Dockerfile", platforms: "linux/amd64" }
- - { tag: "server-cuda", dockerfile: ".devops/server-cuda.Dockerfile", platforms: "linux/amd64" }
- - { tag: "light-rocm", dockerfile: ".devops/main-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
+ - { tag: "server-cuda", dockerfile: ".devops/llama-server-cuda.Dockerfile", platforms: "linux/amd64" }
+ - { tag: "light-rocm", dockerfile: ".devops/llama-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
  - { tag: "full-rocm", dockerfile: ".devops/full-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
- - { tag: "server-rocm", dockerfile: ".devops/server-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
- - { tag: "light-intel", dockerfile: ".devops/main-intel.Dockerfile", platforms: "linux/amd64" }
- - { tag: "server-intel", dockerfile: ".devops/server-intel.Dockerfile", platforms: "linux/amd64" }
+ - { tag: "server-rocm", dockerfile: ".devops/llama-server-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
+ - { tag: "light-intel", dockerfile: ".devops/llama-intel.Dockerfile", platforms: "linux/amd64" }
+ - { tag: "server-intel", dockerfile: ".devops/llama-server-intel.Dockerfile", platforms: "linux/amd64" }
  steps:
  - name: Check out the repo
  uses: actions/checkout@v4

diff --git a/README-sycl.md b/README-sycl.md
@@ -99,14 +99,14 @@ The docker build option is currently limited to *intel GPU* targets.
 ### Build image
 ```sh
 # Using FP16
-docker build -t llama-cpp-sycl --build-arg="LLAMA_SYCL_F16=ON" -f .devops/main-intel.Dockerfile .
+docker build -t llama-cpp-sycl --build-arg="LLAMA_SYCL_F16=ON" -f .devops/llama-intel.Dockerfile .
 ```
 
 *Notes*:
 
 To build in default FP32 *(Slower than FP16 alternative)*, you can remove the `--build-arg="LLAMA_SYCL_F16=ON"` argument from the previous command.
 
-You can also use the `.devops/server-intel.Dockerfile`, which builds the *"server"* alternative.
+You can also use the `.devops/llama-server-intel.Dockerfile`, which builds the *"server"* alternative.
 
 ### Run container
 

diff --git a/README.md b/README.md
@@ -556,7 +556,7 @@ Building the program with BLAS support may lead to some performance improvements
 
  ```sh
  # Build the image
- docker build -t llama-cpp-vulkan -f .devops/main-vulkan.Dockerfile .
+ docker build -t llama-cpp-vulkan -f .devops/llama-vulkan.Dockerfile .
 
  # Then, use it:
  docker run -it --rm -v "$(pwd):/app:Z" --device /dev/dri/renderD128:/dev/dri/renderD128 --device /dev/dri/card1:/dev/dri/card1 llama-cpp-vulkan -m "/app/models/YOUR_MODEL_FILE" -p "Building a website can be done in 10 simple steps:" -n 400 -e -ngl 33
@@ -936,8 +936,8 @@ Assuming one has the [nvidia-container-toolkit](https://github.com/NVIDIA/nvidia
 
 ```bash
 docker build -t local/llama.cpp:full-cuda -f .devops/full-cuda.Dockerfile .
-docker build -t local/llama.cpp:light-cuda -f .devops/main-cuda.Dockerfile .
-docker build -t local/llama.cpp:server-cuda -f .devops/server-cuda.Dockerfile .
+docker build -t local/llama.cpp:light-cuda -f .devops/llama-cuda.Dockerfile .
+docker build -t local/llama.cpp:server-cuda -f .devops/llama-server-cuda.Dockerfile .
 ```
 
 You may want to pass in some different `ARGS`, depending on the CUDA environment supported by your container host, as well as the GPU architecture.