xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-09 05:37:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

[BugFix] Fix initialization of draft model. (#29319)

Browse Source 
Signed-off-by: Andrey Khalyavin <halyavin@yandex-team.ru>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
This commit is contained in:
Andrey Khalyavin 2025-11-26 02:45:58 +03:00 committed by GitHub
parent 7df0289782
commit de75b0bb70
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/v1/worker/gpu_model_runner.py
View File

@ -3460,6 +3460,10 @@ class GPUModelRunner(
scope="local", scope="local",
) )
prepare_communication_buffer_for_model(self.model) prepare_communication_buffer_for_model(self.model)
if (drafter := getattr(self, "drafter", None)) and (
drafter_model := getattr(drafter, "model", None)
):
prepare_communication_buffer_for_model(drafter_model)
mm_config = self.model_config.multimodal_config mm_config = self.model_config.multimodal_config
self.is_multimodal_pruning_enabled = ( self.is_multimodal_pruning_enabled = (
supports_multimodal_pruning(self.get_model()) supports_multimodal_pruning(self.get_model())