mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-30 21:34:36 +00:00
6f1d9d71f4
Some checks are pending
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Nix CI / nix-build (macos-latest) (push) Waiting to run
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
flake8 Lint / Lint (push) Waiting to run
Python Type-Check / pyright type-check (push) Waiting to run
* Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS * Set ROCM_DOCKER_ARCH as string due it incorrectly build and cause OOM exit code
46 lines
1.0 KiB
Docker
46 lines
1.0 KiB
Docker
ARG UBUNTU_VERSION=22.04
|
|
|
|
# This needs to generally match the container host's environment.
|
|
ARG ROCM_VERSION=5.6
|
|
|
|
# Target the CUDA build image
|
|
ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
|
|
|
|
FROM ${BASE_ROCM_DEV_CONTAINER} AS build
|
|
|
|
# Unless otherwise specified, we make a fat build.
|
|
# List from https://github.com/ggerganov/llama.cpp/pull/1087#issuecomment-1682807878
|
|
# This is mostly tied to rocBLAS supported archs.
|
|
ARG ROCM_DOCKER_ARCH="\
|
|
gfx803 \
|
|
gfx900 \
|
|
gfx906 \
|
|
gfx908 \
|
|
gfx90a \
|
|
gfx1010 \
|
|
gfx1030 \
|
|
gfx1100 \
|
|
gfx1101 \
|
|
gfx1102"
|
|
|
|
COPY requirements.txt requirements.txt
|
|
COPY requirements requirements
|
|
|
|
RUN pip install --upgrade pip setuptools wheel \
|
|
&& pip install -r requirements.txt
|
|
|
|
WORKDIR /app
|
|
|
|
COPY . .
|
|
|
|
# Set nvcc architecture
|
|
ENV AMDGPU_TARGETS=${ROCM_DOCKER_ARCH}
|
|
# Enable ROCm
|
|
ENV GGML_HIPBLAS=1
|
|
ENV CC=/opt/rocm/llvm/bin/clang
|
|
ENV CXX=/opt/rocm/llvm/bin/clang++
|
|
|
|
RUN make -j$(nproc) llama-cli
|
|
|
|
ENTRYPOINT [ "/app/llama-cli" ]
|