Upgrade vLLM to v0.10.0 (#1927)

### What this PR does / why we need it?
- Upgrade to v0.10.0
- Drop v0.9.2 version compatibility
- Add patch for
`vllm_ascend/patch/worker/patch_common/patch_sampler_gather_logprobs.py`
as workaround of
f3a683b7c9
for v0.10.0 and also add e2e test `test_models_prompt_logprobs`
- Pin transformers<4.54.0 as workaround of
https://github.com/vllm-project/vllm-ascend/issues/2034

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

### How was this patch tested?
- Test locally:
`VLLM_USE_MODELSCOPE=true pytest -sv
tests/e2e/singlecard/test_offline_inference.py::test_models_prompt_logprobs`
- CI passed

- vLLM version: v0.9.2
- vLLM main:
7728dd77bb

---------

Signed-off-by: Yikun Jiang <yikunkero@gmail.com>

vllm_ascend/core/scheduler.py

@@ -32,8 +32,6 @@ from vllm.v1.outputs import ModelRunnerOutput
 from vllm.v1.request import Request, RequestStatus
 from vllm.v1.structured_output import StructuredOutputManager
 
-from vllm_ascend.utils import vllm_version_is
-
 
 class AscendScheduler(Scheduler):
     """This Scheduler extends vllm's original v1 scheduler
@@ -283,23 +281,12 @@ class AscendScheduler(Scheduler):
                     # allow the lower-priority requests to be scheduled.
                     req_index += 1
                     continue
-                if vllm_version_is("0.9.2"):
-                    num_draft_tokens = max(
-                        num_new_tokens + request.num_computed_tokens -
-                        request.num_tokens, 0)
 
                 while True:
-                    if vllm_version_is("0.9.2"):
-                        new_blocks = self.kv_cache_manager.allocate_slots(
-                            request,
-                            num_new_tokens,
-                            num_draft_tokens=num_draft_tokens,
-                            num_lookahead_tokens=self.num_lookahead_tokens)
-                    else:
-                        new_blocks = self.kv_cache_manager.allocate_slots(
-                            request,
-                            num_new_tokens,
-                            num_lookahead_tokens=self.num_lookahead_tokens)
+                    new_blocks = self.kv_cache_manager.allocate_slots(
+                        request,
+                        num_new_tokens,
+                        num_lookahead_tokens=self.num_lookahead_tokens)
                     if new_blocks is None:
                         # The request cannot be scheduled.
                         # Preempt the lowest-priority request.