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

[Feature] Merge branch 'Qwen3-Next' into main && Support Qwen-next (#222)

Browse Source 
Signed-off-by: xyDong0223 <dongxinyu03@baidu.com>
Co-authored-by: xyDong0223 <dongxinyu03@baidu.com>
This commit is contained in:
chanzhennan
2026-02-28 11:15:50 +08:00
committed by GitHub
parent 153093d3b3
commit 82544aa0cc
17 changed files with 2668 additions and 1532 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_kunlun/v1/sample/spec_decode/eagle.py
View File

@@ -337,5 +337,5 @@ def prepare_next_token_ids_padded(
return next_token_ids, valid_sampled_tokens_count
EagleProposer.propose = propose
# EagleProposer.propose = propose
EagleProposer.prepare_next_token_ids_padded = prepare_next_token_ids_padded