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, 08:45 UTC
[CPU] Add action to automatically label CPU related PRs (#30678)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Fadi Arafeh committed
Dec 17, 2025 at 04:21 UTC
bb5ac1fe38c9fcc7bafaee47fd45c8d1696ad176
1 file changed
+14
.github/mergify.yml
+14
@@ -235,6 +235,20 @@ pull_request_rules:
235
add:
236
- rocm
237
238
+- name: label-cpu
239
+ description: Automatically apply cpu label
240
+ conditions:
241
+ - label != stale
242
+ - files~=^(?!.*kv_offload)(?!.*cpu_offload).*\bcpu.*
243
+ actions:
244
+ label:
245
+ add:
246
+ - cpu
247
+ assign:
248
+ users:
249
+ - "fadara01"
250
+ - "aditew01"
251
+
252
- name: label-structured-output
253
description: Automatically apply structured-output label
254
conditions: