[Misc] upgrade to vllm main (#6646)

### What this PR does / why we need it?
This PR upgrades the core vLLM dependency to a newer version from the
main branch (`13397841ab469cecf1ed425c3f52a9ffc38139b5`). This is
necessary to keep our project up-to-date with the latest features and
fixes from upstream vLLM.

1.
ac32e66cf9
pass file is moved.

- vLLM version: v0.15.0
- vLLM main:
d7e17aaacd

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: wxsIcey <1790571317@qq.com>
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
Co-authored-by: wxsIcey <1790571317@qq.com>

vllm_ascend/compilation/passes/allreduce_rmsnorm_fusion_pass.py

@@ -17,13 +17,19 @@
 import torch
 import torch._inductor.pattern_matcher as pm
 from torch._inductor.pattern_matcher import PatternMatcherPass, PatternPrettyPrinter
-from vllm.compilation.vllm_inductor_pass import VllmInductorPass
 from vllm.config import VllmConfig
 from vllm.config.compilation import Range
 from vllm.distributed import get_tensor_model_parallel_world_size, tensor_model_parallel_all_reduce
 from vllm.distributed.parallel_state import get_tp_group
 from vllm.logger import logger
 
+from vllm_ascend.utils import vllm_version_is
+
+if vllm_version_is("0.15.0"):
+    from vllm.compilation.vllm_inductor_pass import VllmInductorPass  # type: ignore
+else:
+    from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
+
 # computation-communication tiling block is 512
 ALLREDUCE_NORM_FUSE_THREHOLD = 512
 

vllm_ascend/compilation/passes/norm_quant_fusion_pass.py

@@ -18,12 +18,16 @@
 import torch
 import torch._inductor.pattern_matcher as pm
 from torch._inductor.pattern_matcher import PatternMatcherPass
-from vllm.compilation.vllm_inductor_pass import VllmInductorPass
 from vllm.config import VllmConfig
 from vllm.config.compilation import Range
 from vllm.logger import logger
 
-from vllm_ascend.utils import enable_custom_op
+from vllm_ascend.utils import enable_custom_op, vllm_version_is
+
+if vllm_version_is("0.15.0"):
+    from vllm.compilation.vllm_inductor_pass import VllmInductorPass  # type: ignore
+else:
+    from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
 
 
 class AddRMSNormQuantPattern:

vllm_ascend/compilation/passes/qknorm_rope_fusion_pass.py

@@ -18,7 +18,6 @@
 import torch
 import torch._inductor.pattern_matcher as pm
 from torch._inductor.pattern_matcher import PatternMatcherPass, PatternPrettyPrinter
-from vllm.compilation.vllm_inductor_pass import VllmInductorPass
 from vllm.config import VllmConfig, get_layers_from_vllm_config
 from vllm.config.compilation import Range
 from vllm.logger import logger
@@ -27,7 +26,9 @@ from vllm_ascend.utils import vllm_version_is
 
 if vllm_version_is("v0.15.0"):
     from vllm.attention.layer import Attention  # type: ignore
+    from vllm.compilation.vllm_inductor_pass import VllmInductorPass  # type: ignore
 else:
+    from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
     from vllm.model_executor.layers.attention import Attention