[Performance] Add async exponential while model executing (#4501)

### What this PR does / why we need it?
Add a control to enable the exponential distribution operator
overlapping with model executing (default is OFF due to this feature
might not perform well on MOE models, i.e. For Qwen3-30B).
Enable async exponential overlapping will provides performance
improvement.
Also, overlapping the exponential operator with module execution can
cover the performance drop introduced by AICPU-version's exponential
operator.

**UPDATE**: (12/12)
Now our overlap will use the same stream that introduced in this pr:
#4908 .
We move the `do_async_exponential` from `model_runner_v1.py` to
`sampler.py`.
Now we are using `additional_config` to enable async exponential:
Add `"enable_async_exponential": 1` in `addition_config`.
Now we **ONLY** support default exponential/AI-CPU exponential, the old
`"enable_async_exponential": 2` option has been aborted to keep
consistency.

### Does this PR introduce _any_ user-facing change?
**YES**, added a new `additional_config` : `"enable_async_exponential":
1`.
When `enable_async_exponential` is set to 1, we enable the async
exponential and overlap with model runner.
When `enable_async_exponential` is set to 0 (default is 0), we disable
the async exponential, but exponential will still running on a different
stream using stream introduced in #4908.

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: YuhanBai <yuhan.bai0830@gmail.com>
Signed-off-by: YuhanBai yuhan.bai0830@gmail.com

tests/e2e/singlecard/test_sampler.py

@@ -47,3 +47,21 @@ def test_models_prompt_logprobs() -> None:
         runner.generate_greedy_logprobs(example_prompts,
                                         max_tokens=5,
                                         num_logprobs=1)
+
+
+def test_exponential_overlap() -> None:
+    example_prompts = [
+        "Hello, my name is",
+    ]
+    sampling_params = SamplingParams(max_tokens=5,
+                                     temperature=1.0,
+                                     top_k=50,
+                                     top_p=0.9)
+
+    with VllmRunner("Qwen/Qwen3-0.6B",
+                    max_model_len=8192,
+                    gpu_memory_utilization=0.7,
+                    additional_config={
+                        "enable_async_exponential": 1,
+                    }) as runner:
+        runner.generate(example_prompts, sampling_params)