@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / f07c1ceaa5
Fork 0

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 17, 06:45 UTC

[FIX] Fix docker build error (#1831) (#1832)

Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>

Allen committed Nov 30, 2023 at 15:06 UTC f07c1ceaa5162e2ad3b127e06b162508dc57e4db
3 files changed +13 -1
Dockerfile
+5
@@ -18,6 +18,11 @@ RUN --mount=type=cache,target=/root/.cache/pip \
18 # image to build pytorch extensions
19 FROM dev AS build
20
21 +# install build dependencies
22 +COPY requirements-build.txt requirements-build.txt
23 +RUN --mount=type=cache,target=/root/.cache/pip \
24 + pip install -r requirements-build.txt
25 +
26 # copy input files
27 COPY csrc csrc
28 COPY setup.py setup.py
pyproject.toml
+2 -1
@@ -1,8 +1,9 @@
1 [build-system]
2 +# Should be mirrored in requirements-build.txt
3 requires = [
4 "ninja",
5 "packaging",
5 - "setuptools",
6 + "setuptools >= 49.4.0",
7 "torch >= 2.1.0",
8 "wheel",
9 ]
requirements-build.txt new
+6
@@ -0,0 +1,6 @@
1 +# Should be mirrored in pyproject.toml
2 +ninja
3 +packaging
4 +setuptools>=49.4.0
5 +torch>=2.1.0
6 +wheel
\ No newline at end of file