Add sleep mode feature for Ascend NPU

[celestialli]

What this PR does / why we need it?

This PR adds sleep mode feature for vllm-ascend, when sleeps, we do mainly two things:

• offload model weights
• discard kv cache

RLHF tools(such as https://github.com/volcengine/verl and https://github.com/OpenRLHF/OpenRLHF) have a strong need of sleep mode to accelerate the training process.

This PR may solve #375 and #320 .

Does this PR introduce any user-facing change?

No existing user interfaces changed.
Users will have two new methods(sleep() and wake_up()) to use.

How was this patch tested?

This PR is tested with Qwen/Qwen2.5-0.5B-Instruct.

At first, we have free NPU memory M1.

After llm = LLM("Qwen/Qwen2.5-0.5B-Instruct", enable_sleep_mode=True) executed, we have free NPU memory M2. M2 < M1.

Then we call llm.sleep(level=1), we have free NPU memory M3.

We have M3 > M2, M3 is very close to M1.

Plus, we have the same output tokens before sleep and after wake up, with the config of SamplingParams(temperature=0, max_tokens=10) and with the same input tokens of course.

This PR is utilizing the CMake procedure of #371 , thanks a lot.

[Switchsyj]

Hello, do I need to build Ascend_C package from source in order to utilize this sleep() feature, as I find that this library might be necessary:

lib_name = find_loaded_library("vllm_ascend_C")

And I encountered this error while importing vllm_ascend.vllm_ascend_C:

ModuleNotFoundError: No module named 'vllm_ascend.vllm_ascend_C