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 11, 21:15 UTC
Address comment to mergify.yml in #30117 (#30219)
Signed-off-by: Zhijian Jiang <Zhijian.Jiang@outlook.com>
Zhijian Jiang committed
Dec 7, 2025 at 19:26 UTC
344b50d5258d7cf3f136416e1dbcd9b5ee99bb00
1 file changed
+2
-2
.github/mergify.yml
+2
-2
@@ -172,7 +172,7 @@ pull_request_rules:
172
- files~=^tests/entrypoints/test_context.py
173
- files~=^vllm/model_executor/models/.*gpt[-_]?oss.*\.py
174
- files~=^vllm/model_executor/layers/.*gpt[-_]?oss.*\.py
175
- - files~=^vllm/entrypoints/harmony_utils.py
175
+ - files~=^vllm/entrypoints/openai/parser/harmony_utils.py
176
- files~=^vllm/entrypoints/tool_server.py
177
- files~=^vllm/entrypoints/tool.py
178
- files~=^vllm/entrypoints/context.py
@@ -390,4 +390,4 @@ pull_request_rules:
390
actions:
391
label:
392
add:
393
- - kv-connector
\ No newline at end of file
393
+ - kv-connector