ensure libbitsandbytes*.so gets included with wheel
Browse files- docker/Dockerfile-base +2 -1
docker/Dockerfile-base
CHANGED
|
@@ -76,9 +76,10 @@ RUN git clone https://github.com/NVIDIA/apex
|
|
| 76 |
# `MAX_JOBS=1` disables parallel building to avoid cpu memory OOM when building image on GitHub Action (standard) runners
|
| 77 |
RUN cd apex && MAX_JOBS=1 python3 -m pip install --global-option="--cpp_ext" --global-option="--cuda_ext" --no-cache -v --disable-pip-version-check .
|
| 78 |
|
| 79 |
-
RUN mkdir /workspace/wheels
|
| 80 |
COPY --from=deepspeed-builder /workspace/DeepSpeed/dist/deepspeed-*.whl wheels
|
| 81 |
COPY --from=bnb-builder /workspace/bitsandbytes/dist/bitsandbytes-*.whl wheels
|
|
|
|
| 82 |
COPY --from=flash-attn-builder /workspace/flash-attention/dist/flash_attn-*.whl wheels
|
| 83 |
COPY --from=flash-attn-builder /workspace/flash-attention/csrc/fused_dense_lib/dist/fused_dense_lib-*.whl wheels
|
| 84 |
COPY --from=flash-attn-builder /workspace/flash-attention/csrc/xentropy/dist/xentropy_cuda_lib-*.whl wheels
|
|
|
|
| 76 |
# `MAX_JOBS=1` disables parallel building to avoid cpu memory OOM when building image on GitHub Action (standard) runners
|
| 77 |
RUN cd apex && MAX_JOBS=1 python3 -m pip install --global-option="--cpp_ext" --global-option="--cuda_ext" --no-cache -v --disable-pip-version-check .
|
| 78 |
|
| 79 |
+
RUN mkdir -p /workspace/wheels/bitsandbytes
|
| 80 |
COPY --from=deepspeed-builder /workspace/DeepSpeed/dist/deepspeed-*.whl wheels
|
| 81 |
COPY --from=bnb-builder /workspace/bitsandbytes/dist/bitsandbytes-*.whl wheels
|
| 82 |
+
COPY --from=bnb-builder /workspace/bitsandbytes/bitsandbytes/libbitsandbytes*.so wheels/bitsandbytes
|
| 83 |
COPY --from=flash-attn-builder /workspace/flash-attention/dist/flash_attn-*.whl wheels
|
| 84 |
COPY --from=flash-attn-builder /workspace/flash-attention/csrc/fused_dense_lib/dist/fused_dense_lib-*.whl wheels
|
| 85 |
COPY --from=flash-attn-builder /workspace/flash-attention/csrc/xentropy/dist/xentropy_cuda_lib-*.whl wheels
|