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
[Misc] Add kv-connector label (#25156)
Signed-off-by: NickLucche <nlucches@redhat.com>
Nicolò Lucchesi committed
Sep 18, 2025 at 15:56 UTC
bc19d7598566ae81b3f69b43cbc2bd34aa5497c5
1 file changed
+17
.github/mergify.yml
+17
@@ -302,3 +302,20 @@ pull_request_rules:
302
label:
303
remove:
304
- needs-rebase
305
+
306
+- name: label-kv-connector
307
+ description: Automatically apply kv-connector label
308
+ conditions:
309
+ - or:
310
+ - files~=^examples/online_serving/disaggregated[^/]*/.*
311
+ - files~=^examples/offline_inference/disaggregated[^/]*/.*
312
+ - files~=^examples/others/lmcache/
313
+ - files~=^tests/v1/kv_connector/
314
+ - files~=^vllm/distributed/kv_transfer/
315
+ - title~=(?i)\bP/?D\b
316
+ - title~=(?i)NIXL
317
+ - title~=(?i)LMCache
318
+ actions:
319
+ label:
320
+ add:
321
+ - kv-connector
\ No newline at end of file