Drop 0.11.0 support (#4377)

There is a lot hack code for v0.11.0, which makes the code hard to
upgrade to newer vLLM version. Since v0.11.0 will release soon. Let's
drop v0.11.0 support first. Then we'll upgrade to v0.11.2 soon.


- vLLM version: v0.11.0
- vLLM main:
2918c1b49c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

vllm_ascend/sample/rejection_sampler.py

@@ -6,16 +6,10 @@ import torch.nn as nn
 import vllm.v1.sample.rejection_sampler as rs
 from vllm.v1.sample.metadata import SamplingMetadata
 from vllm.v1.sample.rejection_sampler import (RejectionSampler,
+                                              apply_sampling_constraints,
                                               generate_uniform_probs)
 from vllm.v1.spec_decode.metadata import SpecDecodeMetadata
 
-from vllm_ascend.utils import vllm_version_is
-
-if vllm_version_is("0.11.0"):
-    from vllm.v1.sample.rejection_sampler import compute_probs
-else:
-    from vllm.v1.sample.rejection_sampler import apply_sampling_constraints
-
 PLACEHOLDER_TOKEN_ID = -1
 GREEDY_TEMPERATURE = -1
 # Maximum number of speculative draft tokens allowed per request in a single
@@ -89,19 +83,12 @@ class AscendRejectionSampler(RejectionSampler, nn.Module):
         # [num_tokens, vocab_size]
         # NOTE(woosuk): `target_logits` can be updated in place inside the
         # `compute_probs` function.
-        if vllm_version_is("0.11.0"):
-            target_probs = compute_probs(
-                target_logits,
-                metadata.cu_num_draft_tokens,
-                sampling_metadata,
-            )
-        else:
-            target_logits = apply_sampling_constraints(
-                target_logits,
-                metadata.cu_num_draft_tokens,
-                sampling_metadata,
-            )
-            target_probs = target_logits.softmax(dim=-1, dtype=torch.float32)
+        target_logits = apply_sampling_constraints(
+            target_logits,
+            metadata.cu_num_draft_tokens,
+            sampling_metadata,
+        )
+        target_probs = target_logits.softmax(dim=-1, dtype=torch.float32)
 
         output_token_ids = rejection_sample(
             metadata.draft_token_ids,