xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-18 00:35:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix Granite 3.0 MoE model loading (#12446)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung 2025-01-27 13:26:44 +08:00 committed by GitHub
parent 0cc6b383d7
commit 5204ff5c3f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/model_executor/models/granitemoe.py
View File

@ -348,6 +348,7 @@ class GraniteMoeForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
self.config = config self.config = config
self.lora_config = lora_config self.lora_config = lora_config
self.quant_config = quant_config # Required by MixtralForCausalLM
self.model = GraniteMoeModel(vllm_config=vllm_config, self.model = GraniteMoeModel(vllm_config=vllm_config,
prefix=maybe_prefix(prefix, "model")) prefix=maybe_prefix(prefix, "model"))