root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-12 11:40:17 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

update dockerfile refs

Browse Source
This commit is contained in:
Olivier Chafik 2024-06-10 16:05:11 +01:00
parent 1cc651446d
commit 051633ed2d
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README-sycl.md
View File

@ -99,7 +99,7 @@ The docker build option is currently limited to *intel GPU* targets.
### Build image ### Build image
```sh ```sh
# Using FP16 # Using FP16
docker build -t llama-cpp-sycl --build-arg="LLAMA_SYCL_F16=ON" -f .devops/llama-intel.Dockerfile . docker build -t llama-cpp-sycl --build-arg="LLAMA_SYCL_F16=ON" -f .devops/llama-cli-intel.Dockerfile .
``` ```
*Notes*: *Notes*:

4
README.md
View File

@ -555,7 +555,7 @@ Building the program with BLAS support may lead to some performance improvements
```sh ```sh
# Build the image # Build the image
docker build -t llama-cpp-vulkan -f .devops/llama-vulkan.Dockerfile . docker build -t llama-cpp-vulkan -f .devops/llama-cli-vulkan.Dockerfile .
# Then, use it: # Then, use it:
docker run -it --rm -v "$(pwd):/app:Z" --device /dev/dri/renderD128:/dev/dri/renderD128 --device /dev/dri/card1:/dev/dri/card1 llama-cpp-vulkan -m "/app/models/YOUR_MODEL_FILE" -p "Building a website can be done in 10 simple steps:" -n 400 -e -ngl 33 docker run -it --rm -v "$(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
@ -907,7 +907,7 @@ Assuming one has the [nvidia-container-toolkit](https://github.com/NVIDIA/nvidia
```bash ```bash
docker build -t local/llama.cpp:full-cuda -f .devops/full-cuda.Dockerfile . docker build -t local/llama.cpp:full-cuda -f .devops/full-cuda.Dockerfile .
docker build -t local/llama.cpp:light-cuda -f .devops/llama-cuda.Dockerfile . docker build -t local/llama.cpp:light-cuda -f .devops/llama-cli-cuda.Dockerfile .
docker build -t local/llama.cpp:server-cuda -f .devops/llama-server-cuda.Dockerfile . docker build -t local/llama.cpp:server-cuda -f .devops/llama-server-cuda.Dockerfile .
``` ```