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, 09:30 UTC
[CI/Build] Quoting around > (#9956)
Nikita Furin committed
Nov 2, 2024 at 22:50 UTC
1b73ab2a1f0761a60b28aabe0456a5735de027c5
5 files changed
+5
-5
Dockerfile
+1
-1
@@ -206,7 +206,7 @@ FROM vllm-base AS vllm-openai
206
207
# install additional dependencies for openai api server
208
RUN --mount=type=cache,target=/root/.cache/pip \
209
- pip install accelerate hf_transfer 'modelscope!=1.15.0' bitsandbytes>=0.44.0 timm==0.9.10
209
+ pip install accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.44.0' timm==0.9.10
210
211
ENV VLLM_USAGE_SOURCE production-docker-image
212
Dockerfile.neuron
+1
-1
@@ -31,7 +31,7 @@ RUN --mount=type=bind,source=.git,target=.git \
31
if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh ; fi
32
33
RUN python3 -m pip install -U \
34
- cmake>=3.26 ninja packaging setuptools-scm>=8 wheel jinja2 \
34
+ 'cmake>=3.26' ninja packaging 'setuptools-scm>=8' wheel jinja2 \
35
-r requirements-neuron.txt
36
37
ENV VLLM_TARGET_DEVICE neuron
Dockerfile.ppc64le
+1
-1
@@ -21,7 +21,7 @@ RUN --mount=type=bind,source=.git,target=.git \
21
# These packages will be in rocketce eventually
22
RUN --mount=type=cache,target=/root/.cache/pip \
23
pip install -v --prefer-binary --extra-index-url https://repo.fury.io/mgiessing \
24
- cmake>=3.26 ninja packaging setuptools-scm>=8 wheel jinja2 \
24
+ 'cmake>=3.26' ninja packaging 'setuptools-scm>=8' wheel jinja2 \
25
torch==2.3.1 \
26
-r requirements-cpu.txt \
27
xformers uvloop==0.20.0
Dockerfile.rocm
+1
-1
@@ -52,7 +52,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
52
python3 -m pip uninstall -y torch torchvision \
53
&& python3 -m pip install --pre \
54
torch==2.6.0.dev20240918 \
55
- setuptools-scm>=8 \
55
+ 'setuptools-scm>=8' \
56
torchvision==0.20.0.dev20240918 \
57
--extra-index-url https://download.pytorch.org/whl/nightly/rocm6.2;; \
58
*) ;; esac
Dockerfile.tpu
+1
-1
@@ -25,7 +25,7 @@ ENV VLLM_TARGET_DEVICE="tpu"
25
RUN --mount=type=cache,target=/root/.cache/pip \
26
--mount=type=bind,source=.git,target=.git \
27
python3 -m pip install \
28
- cmake>=3.26 ninja packaging setuptools-scm>=8 wheel jinja2 \
28
+ 'cmake>=3.26' ninja packaging 'setuptools-scm>=8' wheel jinja2 \
29
-r requirements-tpu.txt
30
RUN python3 setup.py develop
31