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, 15:45 UTC
[Bugfix] Fix 3.12 builds on main (#8510)
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Joe Runde committed
Sep 16, 2024 at 18:01 UTC
cca61642e0484212e6cd78b35b4789afed8d19c6
2 files changed
+1
-4
Dockerfile
-4
@@ -182,10 +182,6 @@ FROM vllm-base AS test
182
ADD . /vllm-workspace/
183
184
# install development dependencies (for testing)
185
-# A newer setuptools is required for installing some test dependencies from source that do not publish python 3.12 wheels
186
-# This installation must complete before the test dependencies are collected and installed.
187
-RUN --mount=type=cache,target=/root/.cache/pip \
188
- python3 -m pip install "setuptools>=74.1.1"
185
RUN --mount=type=cache,target=/root/.cache/pip \
186
python3 -m pip install -r requirements-dev.txt
187
requirements-common.txt
+1
@@ -29,4 +29,5 @@ importlib_metadata
29
mistral_common >= 1.4.0
30
pyyaml
31
six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
32
+setuptools>=74.1.1; python_version > '3.11' # Setuptools is used by triton, we need to ensure a modern version is installed for 3.12+ so that it does not try to import distutils, which was removed in 3.12
33
einops # Required for Qwen2-VL.