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 6, 09:30 UTC
[CI] Update mergify tool-calling label paths (#37478)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Flora Feng committed
Mar 19, 2026 at 22:22 UTC
e5a77a5015e663784119d88d7ff9e77ce7419aef
1 file changed
+4
-3
.github/mergify.yml
+4
-3
@@ -333,9 +333,10 @@ pull_request_rules:
333
- label != stale
334
- or:
335
- files~=^tests/tool_use/
336
- - files~=^tests/entrypoints/openai/tool_parsers/
337
- - files=tests/entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py
338
- - files~=^vllm/entrypoints/openai/tool_parsers/
336
+ - files~=^tests/tool_parsers/
337
+ - files~=^tests/entrypoints/openai/.*tool.*
338
+ - files~=^tests/entrypoints/anthropic/.*tool.*
339
+ - files~=^vllm/tool_parsers/
340
- files=docs/features/tool_calling.md
341
- files~=^examples/tool_chat_*
342
- files=examples/offline_inference/chat_with_tools.py