Drop torchair (#4814)

aclgraph is stable and fast now. Let's drop torchair graph mode now.

TODO: some logic to adapt torchair should be cleaned up as well. We'll
do it in the following PR.

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>

vllm_ascend/spec_decode/__init__.py

@@ -20,21 +20,14 @@ from vllm_ascend.spec_decode.eagle_proposer import EagleProposer
 from vllm_ascend.spec_decode.mtp_proposer import MtpProposer
 from vllm_ascend.spec_decode.ngram_proposer import NgramProposer
 from vllm_ascend.spec_decode.suffix_proposer import SuffixDecodingProposer
-from vllm_ascend.torchair.torchair_mtp_proposer import TorchairMtpProposer
 
 
-def get_spec_decode_method(method,
-                           vllm_config,
-                           device,
-                           runner,
-                           is_torchair_graph=False):
+def get_spec_decode_method(method, vllm_config, device, runner):
     if method == "ngram":
         return NgramProposer(vllm_config, device, runner)
     elif method in ("eagle", "eagle3"):
         return EagleProposer(vllm_config, device, runner)
     elif method == "mtp":
-        if is_torchair_graph:
-            return TorchairMtpProposer(vllm_config, device, runner)
         return MtpProposer(vllm_config, device, runner)
     elif method == 'suffix':
         return SuffixDecodingProposer(vllm_config, device, runner)