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
Update reviewers for modelopt related files (#24468)
Zhiyu committed
Sep 8, 2025 at 18:53 UTC
4f87abdcc6efc9946f4d7a205f4bbedf5d53b014
1 file changed
+14
.github/mergify.yml
+14
@@ -273,6 +273,20 @@ pull_request_rules:
273
users:
274
- "sangstar"
275
276
+- name: assign reviewer for modelopt changes
277
+ conditions:
278
+ - or:
279
+ - files~=^vllm/model_executor/layers/quantization/modelopt\.py$
280
+ - files~=^vllm/model_executor/layers/quantization/__init__\.py$
281
+ - files~=^tests/models/quantization/test_modelopt\.py$
282
+ - files~=^tests/quantization/test_modelopt\.py$
283
+ - files~=^tests/models/quantization/test_nvfp4\.py$
284
+ - files~=^docs/features/quantization/modelopt\.md$
285
+ actions:
286
+ assign:
287
+ users:
288
+ - "Edwardf0t1"
289
+
290
- name: remove 'needs-rebase' label when conflict is resolved
291
conditions:
292
- -conflict