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, 04:45 UTC
[CI/Build] Auto tag perf benchmarks related PRs (#19943)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
22quinn committed
Jun 22, 2025 at 01:46 UTC
c305a2109d72cdd37d36595e45c5c0a9cb2ea6d4
1 file changed
+13
.github/mergify.yml
+13
@@ -65,6 +65,19 @@ pull_request_rules:
65
add:
66
- multi-modality
67
68
+- name: label-performance
69
+ description: Automatically apply performance label
70
+ conditions:
71
+ - or:
72
+ - files~=^benchmarks/
73
+ - files~=^vllm/benchmarks/
74
+ - files~=^tests/benchmarks/
75
+ - files~=^\.buildkite/nightly-benchmarks/
76
+ actions:
77
+ label:
78
+ add:
79
+ - performance
80
+
81
- name: label-qwen
82
description: Automatically apply qwen label
83
conditions: