tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

flash attn pip install (#426)

Browse Source 
* flash attn pip

* add packaging

* add packaging to apt get

* install flash attn in dockerfile

* remove unused whls

* add wheel

* clean up pr

fix packaging requirement for ci
upgrade pip for ci
skip build isolation for requiremnents to get flash-attn working
install flash-attn seperately

* install wheel for ci

* no flash-attn for basic cicd

* install flash-attn as pip extras

---------

Co-authored-by: Ubuntu <mgh@mgh-vm.wsyvwcia0jxedeyrchqg425tpb.ax.internal.cloudapp.net>
Co-authored-by: mhenrichsen <some_email@hey.com>
Co-authored-by: Mads Henrichsen <mads@BrbartiendeMads.lan>
Co-authored-by: Wing Lian <wing.lian@gmail.com>
This commit is contained in:
mhenrichsen
2023-08-19 01:00:27 +02:00
committed by GitHub
parent 06edf175ac
commit cf6654769a
6 changed files with 15 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docker/Dockerfile
View File

@@ -16,9 +16,9 @@ RUN git clone --depth=1 https://github.com/OpenAccess-AI-Collective/axolotl.git
# If AXOLOTL_EXTRAS is set, append it in brackets
RUN cd axolotl && \
if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
pip install -e .[$AXOLOTL_EXTRAS]; \
pip install -e .[flash-attn,$AXOLOTL_EXTRAS]; \
else \
pip install -e .; \
pip install -e .[flash-attn]; \
fi
# fix so that git fetch/pull from remote works

27
docker/Dockerfile-base
View File

@@ -31,26 +31,6 @@ WORKDIR /workspace
RUN python3 -m pip install --upgrade pip && pip3 install packaging && \
python3 -m pip install --no-cache-dir -U torch==${PYTORCH_VERSION}+cu${CUDA} --extra-index-url https://download.pytorch.org/whl/cu$CUDA
FROM base-builder AS flash-attn-builder
WORKDIR /workspace
ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
RUN git clone https://github.com/Dao-AILab/flash-attention.git && \
cd flash-attention && \
git checkout v2.0.4 && \
python3 setup.py bdist_wheel && \
cd csrc/fused_dense_lib && \
python3 setup.py bdist_wheel && \
cd ../xentropy && \
python3 setup.py bdist_wheel && \
cd ../rotary && \
python3 setup.py bdist_wheel && \
cd ../layer_norm && \
python3 setup.py bdist_wheel
FROM base-builder AS deepspeed-builder
ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
@@ -90,13 +70,8 @@ RUN mkdir -p /workspace/wheels/bitsandbytes
COPY --from=deepspeed-builder /workspace/DeepSpeed/dist/deepspeed-*.whl wheels
COPY --from=bnb-builder /workspace/bitsandbytes/dist/bitsandbytes-*.whl wheels
COPY --from=bnb-builder /workspace/bitsandbytes/bitsandbytes/libbitsandbytes*.so wheels/bitsandbytes
COPY --from=flash-attn-builder /workspace/flash-attention/dist/flash_attn-*.whl wheels
COPY --from=flash-attn-builder /workspace/flash-attention/csrc/fused_dense_lib/dist/fused_dense_lib-*.whl wheels
COPY --from=flash-attn-builder /workspace/flash-attention/csrc/xentropy/dist/xentropy_cuda_lib-*.whl wheels
COPY --from=flash-attn-builder /workspace/flash-attention/csrc/rotary/dist/rotary_emb-*.whl wheels
COPY --from=flash-attn-builder /workspace/flash-attention/csrc/layer_norm/dist/dropout_layer_norm-*.whl wheels
RUN pip3 install wheels/deepspeed-*.whl wheels/flash_attn-*.whl wheels/fused_dense_lib-*.whl wheels/xentropy_cuda_lib-*.whl wheels/rotary_emb-*.whl wheels/dropout_layer_norm-*.whl
RUN pip3 install wheels/deepspeed-*.whl
RUN cd /workspace/builds/bitsandbytes && python3 setup.py install
RUN git lfs install --skip-repo
RUN pip3 install awscli && \