A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 22:00 UTC
[Bugfix][TPU] Fix outlines installation in TPU Dockerfile (#6256)
Woosuk Kwon committed
Jul 9, 2024 at 02:56 UTC
08c5bdecae5c5186c39a1d1ff444c3bf01f7fa0e
1 file changed
+7
-3
Dockerfile.tpu
+7
-3
@@ -2,11 +2,8 @@ ARG NIGHTLY_DATE="20240601"
2
ARG BASE_IMAGE="us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/xla:nightly_3.10_tpuvm_$NIGHTLY_DATE"
3
4
FROM $BASE_IMAGE
5
-
5
WORKDIR /workspace
7
-COPY . /workspace/vllm
6
9
-ENV VLLM_TARGET_DEVICE="tpu"
7
# Install aiohttp separately to avoid build errors.
8
RUN pip install aiohttp
9
# Install the TPU and Pallas dependencies.
@@ -14,6 +11,13 @@ RUN pip install torch_xla[tpu] -f https://storage.googleapis.com/libtpu-releases
11
RUN pip install torch_xla[pallas] -f https://storage.googleapis.com/jax-releases/jax_nightly_releases.html -f https://storage.googleapis.com/jax-releases/jaxlib_nightly_releases.html
12
13
# Build vLLM.
14
+COPY . /workspace/vllm
15
+ENV VLLM_TARGET_DEVICE="tpu"
16
RUN cd /workspace/vllm && python setup.py develop
17
18
+# Re-install outlines to avoid dependency errors.
19
+# The outlines version must follow requirements-common.txt.
20
+RUN pip uninstall outlines -y
21
+RUN pip install "outlines>=0.0.43"
22
+
23
CMD ["/bin/bash"]