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>

.github/workflows/_e2e_test.yaml

@@ -107,7 +107,6 @@ jobs:
 
           # ------------------------------------ v1 spec decode test ------------------------------------ #
           pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py
-          pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_torchair_correctness.py
           pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py
 
   e2e-2-cards:
@@ -170,10 +169,6 @@ jobs:
         if: ${{ inputs.type == 'light' }}
         run: |
           pytest -sv tests/e2e/multicard/test_qwen3_moe.py::test_models_distributed_Qwen3_MOE_TP2_WITH_EP
-          pytest -sv tests/e2e/multicard/test_torchair_graph_mode.py::test_e2e_qwen3_moe_with_torchair
-          pytest -sv tests/e2e/multicard/test_torchair_graph_mode.py::test_e2e_deepseekv2lite_with_torchair
-          pytest -sv tests/e2e/multicard/test_torchair_graph_mode.py::test_e2e_deepseekv2lite_with_torchair_v1scheduler
-          pytest -sv tests/e2e/multicard/test_torchair_graph_mode.py::test_e2e_deepseekv2lite_with_nz
 
       - name: Run vllm-project/vllm-ascend test (full)
         env:
@@ -183,7 +178,6 @@ jobs:
         run: |
           pytest -sv tests/e2e/multicard/test_quantization.py
           pytest -sv tests/e2e/multicard/test_aclgraph_capture_replay.py
-          pytest -sv tests/e2e/multicard/test_torchair_graph_mode.py
           pytest -sv tests/e2e/multicard/test_full_graph_mode.py
           pytest -sv tests/e2e/multicard/test_data_parallel.py
           pytest -sv tests/e2e/multicard/test_expert_parallel.py