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 5, 22:15 UTC
[CI] Add xpu auto-label rule for Intel GPU/XPU PRs (#38320)
Signed-off-by: wendyliu235 <wenjun.liu@intel.com>
wenjun liu committed
Mar 27, 2026 at 14:22 UTC
c2b17d71afc0256647840238b4e1e6b9fd6c4fa1
1 file changed
+30
.github/mergify.yml
+30
@@ -234,6 +234,36 @@ pull_request_rules:
234
add:
235
- rocm
236
237
+- name: label-xpu
238
+ description: Automatically apply intel-gpu label
239
+ conditions:
240
+ - label != stale
241
+ - or:
242
+ - files~=^docker/Dockerfile.xpu
243
+ - files~=^\\.buildkite/intel_jobs/
244
+ - files=\.buildkite/ci_config_intel.yaml
245
+ - files=vllm/model_executor/layers/fused_moe/xpu_fused_moe.py
246
+ - files=vllm/model_executor/kernels/linear/mixed_precision/xpu.py
247
+ - files=vllm/model_executor/kernels/linear/scaled_mm/xpu.py
248
+ - files=vllm/distributed/device_communicators/xpu_communicator.py
249
+ - files=vllm/v1/attention/backends/mla/xpu_mla_sparse.py
250
+ - files=vllm/v1/attention/ops/xpu_mla_sparse.py
251
+ - files=vllm/v1/worker/xpu_worker.py
252
+ - files=vllm/v1/worker/xpu_model_runner.py
253
+ - files=vllm/_xpu_ops.py
254
+ - files~=^vllm/lora/ops/xpu_ops
255
+ - files=vllm/lora/punica_wrapper/punica_xpu.py
256
+ - files=vllm/platforms/xpu.py
257
+ - title~=(?i)Intel gpu
258
+ - title~=(?i)XPU
259
+ - title~=(?i)Intel
260
+ - title~=(?i)BMG
261
+ - title~=(?i)Arc
262
+ actions:
263
+ label:
264
+ add:
265
+ - intel-gpu
266
+
267
- name: label-cpu
268
description: Automatically apply cpu label
269
conditions: