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 14, 05:30 UTC
[Misc] collect flashinfer version in collect_env.py (#24378)
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Ye (Charlotte) Qi committed
Sep 6, 2025 at 20:30 UTC
81c53ef55c01203a2be39f97acfc9f40abe3686b
1 file changed
+2
vllm/collect_env.py
+2
@@ -74,6 +74,7 @@ DEFAULT_CONDA_PATTERNS = {
74
"zmq",
75
"nvidia",
76
"pynvml",
77
+ "flashinfer-python",
78
}
79
80
DEFAULT_PIP_PATTERNS = {
@@ -89,6 +90,7 @@ DEFAULT_PIP_PATTERNS = {
90
"zmq",
91
"nvidia",
92
"pynvml",
93
+ "flashinfer-python",
94
}
95
96