@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 774cd1d3bf
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 16, 19:30 UTC

[CI/Build] bump minimum cmake version (#6999)

Daniele committed Aug 13, 2024 at 01:29 UTC 774cd1d3bf7890c6abae6c7ace798c4a376b2b20
4 files changed +3 -5
CMakeLists.txt
+1 -1
@@ -1,4 +1,4 @@
1 -cmake_minimum_required(VERSION 3.21)
1 +cmake_minimum_required(VERSION 3.26)
2
3 project(vllm_extensions LANGUAGES CXX)
4
pyproject.toml
+1 -1
@@ -1,7 +1,7 @@
1 [build-system]
2 # Should be mirrored in requirements-build.txt
3 requires = [
4 - "cmake>=3.21",
4 + "cmake>=3.26",
5 "ninja",
6 "packaging",
7 "setuptools >= 49.4.0",
requirements-build.txt
+1 -1
@@ -1,5 +1,5 @@
1 # Should be mirrored in pyproject.toml
2 -cmake>=3.21
2 +cmake>=3.26
3 ninja
4 packaging
5 setuptools>=49.4.0
requirements-common.txt
-2
@@ -1,5 +1,3 @@
1 -cmake >= 3.21
2 -ninja # For faster builds.
1 psutil
2 sentencepiece # Required for LLaMA tokenizer.
3 numpy < 2.0.0