Upgrade to 0.11.1 newest vllm commit (#3982)

### What this PR does / why we need it?
adapt vllm-ascend main branch with vllm releases/v0.11.1

fix `forward context not set` in test_vlm.py caused by:
https://github.com/vllm-project/vllm/pull/23207

fix import `cdiv round` failed caused by:
https://github.com/vllm-project/vllm/pull/27188

fix import `init_cached_hf_modules` failed caused by:
https://github.com/vllm-project/vllm/pull/27567

adapt triton kernel `fused_recurrent_gated_delta_rule_fwd_kernel` caused
by: https://github.com/vllm-project/vllm/pull/27654
- remove unused code in sigmoid_gating.py
- `class FusedRecurrentFunction` , `fused_recurrent_gated_delta_rule`,
`fused_recurrent_gated_delta_rule_fwd`

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
CI 


- vLLM version: v0.11.0
- vLLM main:
83f478bb19

Signed-off-by: 22dimensions <waitingwind@foxmail.com>

vllm_ascend/torchair/models/torchair_deepseek_v2.py

@@ -670,6 +670,8 @@ class TorchairDeepseekV2MLAAttention(DeepseekV2MLAAttention):
                 if self.q_lora_rank is not None else None,
                 q_proj=self.q_proj
                 if self.q_lora_rank is None else self.q_b_proj,
+                q_b_proj=self.q_b_proj
+                if self.q_lora_rank is not None else None,
                 kv_a_proj_with_mqa=self.kv_a_proj_with_mqa,
                 kv_a_layernorm=self.kv_a_layernorm,
                 kv_b_proj=self.kv_b_proj,

vllm_ascend/torchair/torchair_attention.py

@@ -26,7 +26,13 @@ from vllm.attention.backends.abstract import (AttentionImpl, AttentionLayer,
                                               AttentionType)
 from vllm.attention.backends.utils import PAD_SLOT_ID
 from vllm.config import VllmConfig
-from vllm.utils import cdiv
+
+from vllm_ascend.utils import vllm_version_is
+
+if vllm_version_is("0.11.0"):
+    from vllm.utils import cdiv
+else:
+    from vllm.utils.math_utils import cdiv
 
 from vllm_ascend.attention.attention_v1 import (AscendAttentionBackend,
                                                 AscendAttentionMetadataBuilder,

vllm_ascend/torchair/torchair_mla.py

@@ -13,7 +13,13 @@ from vllm.config import VllmConfig, get_current_vllm_config
 from vllm.distributed import get_tensor_model_parallel_world_size
 from vllm.model_executor.layers.linear import (LinearBase,
                                                UnquantizedLinearMethod)
-from vllm.utils import cdiv, round_down
+
+from vllm_ascend.utils import vllm_version_is
+
+if vllm_version_is("0.11.0"):
+    from vllm.utils import cdiv, round_down
+else:
+    from vllm.utils.math_utils import cdiv, round_down
 
 import vllm_ascend.envs as envs_ascend
 from vllm_ascend.ascend_config import get_ascend_config

vllm_ascend/torchair/torchair_sfa.py

@@ -14,7 +14,13 @@ from vllm.config import VllmConfig, get_current_vllm_config
 from vllm.distributed import get_tensor_model_parallel_world_size, get_tp_group
 from vllm.model_executor.layers.linear import (LinearBase,
                                                UnquantizedLinearMethod)
-from vllm.utils import cdiv, round_down
+
+from vllm_ascend.utils import vllm_version_is
+
+if vllm_version_is("0.11.0"):
+    from vllm.utils import cdiv, round_down
+else:
+    from vllm.utils.math_utils import cdiv, round_down
 
 import vllm_ascend.envs as envs_ascend
 from vllm_ascend.ascend_config import get_ascend_config