98af5388ba
* bump flash attention 2.5.8 -> 2.6.1 * use triton implementation of cross entropy from flash attn * add smoke test for flash attn cross entropy patch * fix args to xentropy.apply * handle tuple from triton loss fn * ensure the patch tests run independently * use the wrapper already built into flash attn for cross entropy * mark pytest as forked for patches * use pytest xdist instead of forked, since cuda doesn't like forking * limit to 1 process and use dist loadfile for pytest * change up pytest for fixture to reload transformers w monkeypathc
41 lines
1.3 KiB
Django/Jinja
41 lines
1.3 KiB
Django/Jinja
FROM winglian/axolotl-base:{{ BASE_TAG }}
|
|
|
|
ENV TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"
|
|
ENV AXOLOTL_EXTRAS="{{ AXOLOTL_EXTRAS }}"
|
|
ENV AXOLOTL_ARGS="{{ AXOLOTL_ARGS }}"
|
|
ENV CUDA="{{ CUDA }}"
|
|
ENV BNB_CUDA_VERSION="{{ CUDA }}"
|
|
ENV PYTORCH_VERSION="{{ PYTORCH_VERSION }}"
|
|
ENV GITHUB_REF="{{ GITHUB_REF }}"
|
|
ENV GITHUB_SHA="{{ GITHUB_SHA }}"
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y --allow-change-held-packages vim curl nano libnccl2 libnccl-dev
|
|
|
|
WORKDIR /workspace
|
|
|
|
RUN git clone --depth=1 https://github.com/axolotl-ai-cloud/axolotl.git
|
|
|
|
WORKDIR /workspace/axolotl
|
|
|
|
RUN git fetch origin +$GITHUB_REF && \
|
|
git checkout FETCH_HEAD
|
|
|
|
# If AXOLOTL_EXTRAS is set, append it in brackets
|
|
RUN pip install causal_conv1d
|
|
RUN if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
|
|
pip install -e .[deepspeed,flash-attn,mamba-ssm,galore,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
|
|
else \
|
|
pip install -e .[deepspeed,flash-attn,mamba-ssm,galore] $AXOLOTL_ARGS; \
|
|
fi
|
|
|
|
# So we can test the Docker image
|
|
RUN pip install -r requirements-tests.txt
|
|
|
|
# fix so that git fetch/pull from remote works
|
|
RUN git config remote.origin.fetch "+refs/heads/*:refs/remotes/origin/*" && \
|
|
git config --get remote.origin.fetch
|
|
|
|
# helper for huggingface-login cli
|
|
RUN git config --global credential.helper store
|