tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

fix: docker build failing (#3622)

Browse Source 
* fix: uv leftover docs

* fix: docker build failing

* chore: doc

* fix: remove old pytorch build

* fix: stop recommend flash-attn optional, let transformers pull

* fix: remove ring flash attention from image

* fix: quotes [skip ci]

* chore: naming [skip ci]
This commit is contained in:
NanoCode012
2026-04-24 14:23:09 +07:00
committed by GitHub
parent 901f2356bc
commit 17fc747f99
29 changed files with 62 additions and 119 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docker/Dockerfile
View File

@@ -24,9 +24,9 @@ WORKDIR /workspace/axolotl
# If AXOLOTL_EXTRAS is set, append it in brackets; don't install deepspeed with arm64
RUN pip uninstall -y causal_conv1d
RUN if [ "$TARGETARCH" = "arm64" ]; then \
BASE_EXTRAS="flash-attn,ring-flash-attn,optimizers,ray"; \
BASE_EXTRAS="optimizers,ray"; \
else \
BASE_EXTRAS="deepspeed,flash-attn,ring-flash-attn,optimizers,ray"; \
BASE_EXTRAS="deepspeed,optimizers,ray"; \
fi && \
if [ "$AXOLOTL_EXTRAS" != "" ]; then \
pip install --no-build-isolation -e .[$BASE_EXTRAS,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \

16
docker/Dockerfile-base
View File

@@ -58,19 +58,3 @@ RUN git lfs install --skip-repo && \
# The base image ships with `pydantic==1.8.2` which is not working
pip3 install -U --no-cache-dir pydantic==1.10.10 && \
pip3 cache purge
# Map Python version (e.g., 3.12 -> cp312)
RUN PYTHON_CP="cp$(echo $PYTHON_VERSION | tr -d '.')" && \
# Map PyTorch version (e.g., 2.9.1 -> torch2.9, 2.10.0 -> torch2.10)
TORCH_TAG="torch$(echo $PYTORCH_VERSION | grep -oP '^\d+\.\d+')" && \
# Map architecture
case "$TARGETARCH" in \
amd64) ARCH_TAG="x86_64" ;; \
arm64) ARCH_TAG="aarch64" ;; \
*) echo "Unsupported architecture: $TARGETARCH"; exit 1 ;; \
esac && \
WHL_VERSION="v0.7.16" && \
WHL_FILE="flash_attn-2.8.3+cu${CUDA}${TORCH_TAG}-${PYTHON_CP}-${PYTHON_CP}-linux_${ARCH_TAG}.whl" && \
wget -nv "https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/${WHL_VERSION}/${WHL_FILE}" && \
pip3 install --no-cache-dir "${WHL_FILE}" && \
rm "${WHL_FILE}"

4
docker/Dockerfile-tests
View File

@@ -24,9 +24,9 @@ RUN git fetch origin +$GITHUB_REF && \
# If AXOLOTL_EXTRAS is set, append it in brackets
RUN if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
pip install --no-build-isolation -e .[deepspeed,flash-attn,mamba-ssm,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
pip install --no-build-isolation -e .[deepspeed,mamba-ssm,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
else \
pip install --no-build-isolation -e .[deepspeed,flash-attn,mamba-ssm] $AXOLOTL_ARGS; \
pip install --no-build-isolation -e .[deepspeed,mamba-ssm] $AXOLOTL_ARGS; \
fi
# So we can test the Docker image

4
docker/Dockerfile-uv
View File

@@ -24,9 +24,9 @@ WORKDIR /workspace/axolotl
# If AXOLOTL_EXTRAS is set, append it in brackets; don't install deepspeed with arm64
RUN uv pip uninstall causal_conv1d
RUN if [ "$TARGETARCH" = "arm64" ]; then \
BASE_EXTRAS="flash-attn,ring-flash-attn,optimizers,ray"; \
BASE_EXTRAS="optimizers,ray"; \
else \
BASE_EXTRAS="deepspeed,flash-attn,ring-flash-attn,optimizers,ray"; \
BASE_EXTRAS="deepspeed,optimizers,ray"; \
fi && \
if [ "$AXOLOTL_EXTRAS" != "" ]; then \
uv pip install --no-build-isolation -e .[$BASE_EXTRAS,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \

17
docker/Dockerfile-uv-base
View File

@@ -38,20 +38,3 @@ RUN uv pip install packaging setuptools wheel psutil \
RUN if [ "$TARGETARCH" = "amd64" ]; then \
MAMBA_SKIP_CUDA_BUILD=TRUE CAUSAL_CONV1D_SKIP_CUDA_BUILD=TRUE uv pip install --no-build-isolation mamba_ssm causal_conv1d; \
fi
# Map Python version (e.g., 3.12 -> cp312)
RUN PYTHON_CP="cp$(echo $PYTHON_VERSION | tr -d '.')" && \
# Map PyTorch version (e.g., 2.9.1 -> torch2.9, 2.10.0 -> torch2.10)
TORCH_TAG="torch$(echo $PYTORCH_VERSION | grep -oP '^\d+\.\d+')" && \
LINUX_TAG="manylinux_" && \
# Map architecture
case "$TARGETARCH" in \
amd64) ARCH_TAG="2_24_x86_64.manylinux_2_28_x86_64" ;; \
arm64) ARCH_TAG="2_34_aarch64" ;; \
*) echo "Unsupported architecture: $TARGETARCH"; exit 1 ;; \
esac && \
WHL_VERSION="v0.7.16" && \
WHL_FILE="flash_attn-2.8.3+cu${CUDA}${TORCH_TAG}-${PYTHON_CP}-${PYTHON_CP}-${LINUX_TAG}${ARCH_TAG}.whl" && \
wget -nv "https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/${WHL_VERSION}/${WHL_FILE}" && \
uv pip install --no-cache-dir "${WHL_FILE}" && \
rm "${WHL_FILE}"