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

..

images

[Misc] Add a model loader that utilizes HCCL for weight loading (#2888)

2025-10-23 15:56:07 +08:00

context_parallel.md

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

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

dynamic_batch.md

[Info][main] Corrected the errors in the information (#4055)

2025-11-08 18:48:59 +08:00

eplb_swift_balancer.md

[doc][main] Correct mistakes in doc (#4945)

2025-12-12 19:17:10 +08:00

external_dp.md

[Feat][Doc] Add a load_balance_dp_proxy in examples and external dp doc. (#4265)

2025-11-21 16:33:23 +08:00

Fine_grained_TP.md

[Doc]Add the user_guide doc file regarding fine-grained TP. (#5084)

2025-12-19 16:37:25 +08:00

graph_mode.md

[Feat]Xlite Qwen3-vl Support (#5228)

2025-12-22 16:30:52 +08:00

index.md

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

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

kv_pool.md

[KVPOOL]decode save kvcache (#5168)

2026-01-04 22:22:01 +08:00

large_scale_ep.md

[Doc][P/D] Fix MooncakeConnector's name (#5172)

2025-12-18 22:29:19 +08:00

lora.md

[doc][main] Correct mistakes in doc (#4945)

2025-12-12 19:17:10 +08:00

Multi_Token_Prediction.md

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

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

netloader.md

[Misc] Add a model loader that utilizes HCCL for weight loading (#2888)

2025-10-23 15:56:07 +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

sleep_mode.md

[Doc] Upgrade outdated doc (#4957)

2025-12-12 15:38:29 +08:00

speculative_decoding.md

[Doc] Add user guide of speculative decoding (#5074)

2025-12-16 17:01:44 +08:00

structured_output.md

[Doc] Update structured output doc with upstream link (#4015)

2025-12-11 19:14:29 +08:00

ucm_deployment.md

[Core][Worker] Add UCMConnector for KV Cache Offloading (#4411)

2025-12-16 10:53:30 +08:00