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 15, 13:30 UTC
Fix Python packaging edge cases (#17159)
Signed-off-by: Christian Heimes <christian@python.org>
Christian Heimes committed
Apr 26, 2025 at 00:15 UTC
65e262b93bef6e32482dbeed4027fe4ced680fe9
4 files changed
+2
-2
.gitignore
+1
@@ -3,6 +3,7 @@
3
4
# vllm-flash-attn built from source
5
vllm/vllm_flash_attn/*
6
+!vllm/vllm_flash_attn/__init__.py
7
!vllm/vllm_flash_attn/fa_utils.py
8
9
# Byte-compiled / optimized / DLL files
pyproject.toml
+1
-2
@@ -46,8 +46,7 @@ vllm = "vllm.entrypoints.cli.main:main"
46
47
[tool.setuptools.packages.find]
48
where = ["."]
49
-exclude = ["benchmarks", "csrc", "docs", "examples", "tests*"]
50
-namespaces = false
49
+include = ["vllm*"]
50
51
[tool.yapfignore]
52
ignore_patterns = [