biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V1][Spec Decoding] Use model_loader.get_model() to load models (#18273)

Browse Source 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
This commit is contained in:
Mark McLoughlin
2025-05-23 03:05:44 +01:00
committed by GitHub
parent 04eb88dc80
commit c6b636f9fb
16 changed files with 59 additions and 135 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/model_loader/tensorizer_loader.py
View File

@@ -93,8 +93,8 @@ class TensorizerLoader(BaseModelLoader):
with self.tensorizer_config.open_stream():
pass
def load_model(self, vllm_config: VllmConfig) -> nn.Module:
model_config = vllm_config.model_config
def load_model(self, vllm_config: VllmConfig,
model_config: ModelConfig) -> nn.Module:
parallel_config = vllm_config.parallel_config
self._verify_config(model_config, parallel_config)