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, 04:45 UTC
[XPU][CI] Remove Arc in label-xpu (#39776)
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
xiangdong committed
Apr 14, 2026 at 17:27 UTC
a1993b96fd95ad19cc4b8a1554219ff115939edf
1 file changed
+2
-1
.github/mergify.yml
+2
-1
@@ -264,6 +264,7 @@ pull_request_rules:
264
- files=\.buildkite/ci_config_intel.yaml
265
- files=vllm/model_executor/layers/fused_moe/xpu_fused_moe.py
266
- files=vllm/model_executor/kernels/linear/mixed_precision/xpu.py
267
+ - files=vllm/model_executor/kernels/linear/mxfp8/xpu.py
268
- files=vllm/model_executor/kernels/linear/scaled_mm/xpu.py
269
- files=vllm/distributed/device_communicators/xpu_communicator.py
270
- files=vllm/v1/attention/backends/mla/xpu_mla_sparse.py
@@ -271,6 +272,7 @@ pull_request_rules:
272
- files=vllm/v1/worker/xpu_worker.py
273
- files=vllm/v1/worker/xpu_model_runner.py
274
- files=vllm/_xpu_ops.py
275
+ - files=vllm/kernels/xpu_ops.py
276
- files~=^vllm/lora/ops/xpu_ops
277
- files=vllm/lora/punica_wrapper/punica_xpu.py
278
- files=vllm/platforms/xpu.py
@@ -278,7 +280,6 @@ pull_request_rules:
280
- title~=(?i)XPU
281
- title~=(?i)Intel
282
- title~=(?i)BMG
281
- - title~=(?i)Arc
283
actions:
284
label:
285
add: