[Build] Move numba/quart to requirments and update DS baseline and sync graph typo fix (#1121)

### What this PR does / why we need it?
1. The dependency was introduced by
https://github.com/vllm-project/vllm-ascend/pull/874
- Move numba/quart from requirements-dev to requirments
- Align pyproject.toml with requirements

2. This patch also fix deepseek accuracy baseline which
https://github.com/vllm-project/vllm-ascend/pull/1118 was not addressed.
According to https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite the
gsm8k is about `41.1`

3. This also sync the vLLM upstream changes:
eaa2e51088

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

### How was this patch tested?
CI passed
vllm ascend test (basic workflow)
vllm longterm test (spec decode)

Closes: https://github.com/vllm-project/vllm-ascend/issues/1120

---------

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

vllm_ascend/compilation/piecewise_backend.py

@@ -31,6 +31,8 @@ from vllm.config import VllmConfig
 from vllm.logger import logger
 from vllm.utils import weak_ref_tensors
 
+from vllm_ascend.utils import vllm_version_is
+
 
 @dataclasses.dataclass
 class ConcreteSizeEntry:
@@ -205,7 +207,10 @@ class NPUPiecewiseBackend:
             entry.output = weak_ref_tensors(output)
             entry.aclgraph = aclgraph
 
-            compilation_counter.num_cudagraph_caputured += 1
+            if vllm_version_is("0.9.0"):
+                compilation_counter.num_cudagraph_caputured += 1
+            else:
+                compilation_counter.num_cudagraph_captured += 1
 
             # important: we need to return the output, rather than
             # the weak ref of the output, so that pytorch can correctly