EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

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

Browse Source 
### 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>
This commit is contained in:
lilinsiman
2026-01-05 14:07:54 +08:00
committed by GitHub
parent 50e7934415
commit 52863c4165
8 changed files with 229 additions and 609 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/source/developer_guide/feature_guide/index.md
View File

@@ -9,7 +9,6 @@ patch
ModelRunner_prepare_inputs
disaggregated_prefill
eplb_swift_balancer.md
Multi_Token_Prediction
ACL_Graph
KV_Cache_Pool_Guide
add_custom_aclnn_op