Canlin Guo 65289676b4 [Refactor] Separate _prepare_inputs to _prepare_inputs and _preprocess (#6191) ...

### What this PR does / why we need it?

Align with upstream vLLM. This PR will help downstream vLLM-Omni reduce
the cost for maintaining the _prepare_inputs. Besides, it helps
vLLM-Ascend code more readable. In the future, we can follow closer to
vLLM. The `preprocess` logic is same as GPUModelRunner. We don't need to
maintain it anymore.

### Does this PR introduce _any_ user-facing change?

No

### How was this patch tested?

CI.

- vLLM version: v0.14.0
- vLLM main:
d68209402d

---------

Signed-off-by: gcanlin <canlinguosdu@gmail.com>

2026-01-26 14:05:23 +08:00

..

v2

model runner v2 support triton of penalty (#5854)

2026-01-20 12:26:05 +00:00

__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] support pcp + mtp in full graph (#4572)

2025-12-22 16:13:39 +08:00

model_runner_v1.py

[Refactor] Separate _prepare_inputs to _prepare_inputs and _preprocess (#6191)

2026-01-26 14:05:23 +08:00

npu_input_batch.py

Drop 0.12.0 support (#5146)

2025-12-20 09:38:53 +08:00

pcp_utils.py

[bugfix] fix the complex and potentially problematic generate_kv_idx. (#5957)

2026-01-21 14:21:02 +08:00

worker.py

[Worker] Implement update max_model_len interface for NPUWorker (#6193)

2026-01-26 09:03:33 +08:00