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
[Misc] Update model-specific PR tagging (#19949)
Signed-off-by: Roger Wang <hey@rogerw.me>
Roger Wang committed
Jun 22, 2025 at 05:16 UTC
c76a506bd60f56d364da0de415c48798870e1312
1 file changed
+1
-1
.github/mergify.yml
+1
-1
@@ -45,6 +45,7 @@ pull_request_rules:
45
- files~=^vllm/entrypoints/openai/tool_parsers/llama.*\.py
46
- files~=^vllm/model_executor/models/.*llama.*\.py
47
- files~=^vllm/transformers_utils/configs/.*llama.*\.py
48
+ - title~=(?i)llama
49
actions:
50
label:
51
add:
@@ -87,7 +88,6 @@ pull_request_rules:
88
- files~=^vllm/model_executor/models/.*qwen.*\.py
89
- files~=^vllm/reasoning/.*qwen.*\.py
90
- title~=(?i)Qwen
90
- - body~=(?i)Qwen
91
actions:
92
label:
93
add: