xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 23:15:31 +08:00
Code Issues Packages Projects Releases Wiki Activity

[BugFix]: --enable-lora with model granite-4.0-micro crash (#27733)

Browse Source 
Signed-off-by: zxw <1020938856@qq.com>
This commit is contained in:
yyzxw 2025-11-12 17:03:56 +08:00 committed by GitHub
parent c748355e0d
commit 1761dea1a8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/model_executor/models/granitemoehybrid.py
View File

@ -597,6 +597,9 @@ class GraniteMoeHybridForCausalLM(
"k_proj",
"v_proj",
],
"conv1d": ["conv1d"],
"in_proj": ["in_proj"],
"input_linear": ["input_linear"],
}
embedding_modules = {
"embed_tokens": "input_embeddings",