huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: update docker for mamba

Browse Source
This commit is contained in:
drbh 2024-02-06 21:15:16 +00:00
parent 36a4853c4e
commit 50ca04b052
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
Dockerfile
View File

@ -159,6 +159,12 @@ FROM kernel-builder as megablocks-builder
RUN pip install git+https://github.com/OlivierDehaene/megablocks@181709df192de9a941fdf3a641cdc65a0462996e
# Build mamba kernels
FROM kernel-builder as mamba-builder
WORKDIR /usr/src
COPY server/Makefile-selective-scan Makefile
RUN make build-all
# Text Generation Inference base image
FROM nvidia/cuda:12.1.0-base-ubuntu20.04 as base
@ -205,6 +211,10 @@ COPY --from=eetq-kernels-builder /usr/src/eetq/build/lib.linux-x86_64-cpython-31
# Copy builds artifacts from vllm builder
COPY --from=vllm-builder /usr/src/vllm/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
# Copy build artifacts from mamba builder
COPY --from=mamba-builder /usr/src/mamba/build/lib.linux-x86_64-cpython-310/ /opt/conda/lib/python3.10/site-packages
COPY --from=mamba-builder /usr/src/causal-conv1d/build/lib.linux-x86_64-cpython-310/ /opt/conda/lib/python3.10/site-packages
# Install flash-attention dependencies
RUN pip install einops --no-cache-dir