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, 04:30 UTC
Add ray[default] to wget to run distributed inference out of box (#11265)
Signed-off-by: Jiaxin Shan <seedjeffwan@gmail.com>
Jiaxin Shan committed
Dec 20, 2024 at 13:54 UTC
47a0b615b45efd0a9ed57049d8ca6eff1c249844
2 files changed
+2
-2
Dockerfile
+1
-1
@@ -163,7 +163,7 @@ RUN PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') && \
163
RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
164
&& echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \
165
&& apt-get update -y \
166
- && apt-get install -y ccache software-properties-common git curl sudo vim python3-pip \
166
+ && apt-get install -y ccache software-properties-common git curl wget sudo vim python3-pip \
167
&& apt-get install -y ffmpeg libsm6 libxext6 libgl1 \
168
&& add-apt-repository ppa:deadsnakes/ppa \
169
&& apt-get update -y \
requirements-cuda.txt
+1
-1
@@ -2,7 +2,7 @@
2
-r requirements-common.txt
3
4
# Dependencies for NVIDIA GPUs
5
-ray >= 2.9
5
+ray[default] >= 2.9
6
nvidia-ml-py >= 12.560.30 # for pynvml package
7
torch == 2.5.1
8
# These must be updated alongside torch