[Misc][Spec Decode] support different load config for draft model (#34022)

Signed-off-by: zzhengkai <zzhengkai@devgpu049.ldc1.facebook.com>
Co-authored-by: zzhengkai <zzhengkai@devgpu049.ldc1.facebook.com>
This commit is contained in:
Zhengkai Zhang
2026-02-10 14:52:43 -08:00
committed by GitHub
co-authored by zzhengkai
parent bb2fc8b5e7
commit 6f2f59f2b3
3 changed files with 8 additions and 1 deletions
+1
View File
@@ -1286,6 +1286,7 @@ class SpecDecodeBaseProposer:
model = get_model(
vllm_config=self.vllm_config,
model_config=self.speculative_config.draft_model_config,
load_config=self.speculative_config.draft_load_config,
)
return model