Add MoNe experts pruning support (#50415)
Signed-off-by: Ilya Boytsov <ieboytsov@nebius.com> Signed-off-by: Misha Goin <mgoin64@gmail.com> Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: Ilya Boytsov <ieboytsov@nebius.com> Co-authored-by: Codex <noreply@openai.com> Co-authored-by: Misha Goin <mgoin64@gmail.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Ilya Boytsov
Codex
Misha Goin
Claude Opus 5.5
parent
1484266938
commit
189bbfb9f4
@@ -84,6 +84,12 @@ def initialize_model(
|
||||
if model_class is None:
|
||||
model_class, _ = get_model_architecture(model_config)
|
||||
|
||||
from vllm.model_executor.models.expert_substitution import (
|
||||
as_expert_substitution_model,
|
||||
)
|
||||
|
||||
model_class = as_expert_substitution_model(model_class, model_config)
|
||||
|
||||
if vllm_config.quant_config is not None:
|
||||
configure_quant_config(vllm_config.quant_config, model_class)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user