lilinsiman 52863c4165 [Refactor][EAGLE] 2/N: load model and generate token (#5437) ...

### What this PR does / why we need it?
1. Refactor eagle and mtp function: load_model and generate_token_ids
2. Remove redundant code in mtp and eagle file
3. Refactor the UT of file

2/N of Refactor and merge mtp and eagle
Relational RFC: https://github.com/vllm-project/vllm-ascend/issues/5467

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

### How was this patch tested?
ut and tests

- vLLM version: release/v0.13.0
- vLLM main:
81786c8774

---------

Signed-off-by: lilinsiman <lilinsiman@gmail.com>

2026-01-05 14:07:54 +08:00

..

ACL_Graph.md

[docs] add aclgraph developer guide (#3683)

2025-11-05 10:34:28 +08:00

add_custom_aclnn_op.md

[Kernel] add custom op GmmSwigluQuantWeightNzTensorList (#3804)

2025-11-28 18:06:39 +08:00

context_parallel.md

[doc] Add context parallel user guide (#5358)

2025-12-26 17:03:47 +08:00

disaggregated_prefill.md

[Doc] Update tutorial index (#4920)

2025-12-11 20:53:13 +08:00

eplb_swift_balancer.md

[Doc]Add developer guide of eplb. (#3759)

2025-11-05 18:35:41 +08:00

index.md

[Refactor][EAGLE] 2/N: load model and generate token (#5437)

2026-01-05 14:07:54 +08:00

KV_Cache_Pool_Guide.md

add hyperlink (#4588)

2025-12-02 14:09:03 +08:00

ModelRunner_prepare_inputs.md

[Doc] Update doc (#3836)

2025-10-29 11:03:39 +08:00

patch.md

implement model runner v2 basic framework (#5051)

2025-12-18 15:51:54 +08:00

quantization.md

[Doc]modify the quantization user guide and add a quantization adaptation developer guide (#5554)

2026-01-05 09:12:11 +08:00