zhenwenqi2024 4ed2951400 【Feature】refactor npu_modelrunner for profile_run (#4993) ...

### What this PR does / why we need it?
(1)refactor npu_model_runner for profile_run
(2) move _select_moe_comm_method to ascend_forward_context
(3) delete _init_model_kwargs in npu_model_runner

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

### How was this patch tested?
Na
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Signed-off-by: zhenwenqi2024 <155598497+zhenwenqi2024@users.noreply.github.com>

2025-12-16 17:44:04 +08:00

..

__init__.py

[Misc][V0 Deprecation] Remove Cache Engine Used for V0 Worker (#1878)

2025-07-19 09:42:32 +08:00

block_table.py

[Feature] model_runner refactor (#4764)

2025-12-12 17:27:09 +08:00

model_runner_v1.py

【Feature】refactor npu_modelrunner for profile_run (#4993)

2025-12-16 17:44:04 +08:00

npu_input_batch.py

[Misc] Upgrade vllm hash to 12_14 (#5000)

2025-12-15 19:54:23 +08:00

worker_v1.py

vllm-ascend support Ascend950 with Qwen dense model. (#4228)

2025-12-12 15:50:57 +08:00