Skip to content

[config] Expose get_total_num_hidden_layers() in ModelConfig #28961

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Nov 19, 2025
Merged

[config] Expose get_total_num_hidden_layers() in ModelConfig #28961

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e84d214
[config] Expose `get_total_num_hidden_layers()` in ModelConfig
ptovam Nov 18, 2025
b6839e4
Merge branch 'main' into get_total_num_hidden_layers
yewentao256 Nov 18, 2025
b06a745
Merge branch 'main' into get_total_num_hidden_layers
DarkLight1337 Nov 19, 2025
14af123
Merge branch 'main' into get_total_num_hidden_layers
ptovam Nov 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 10 additions & 5 deletions vllm/config/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1369,11 +1369,7 @@ def get_num_experts(self) -> int:
# Coerce to 0 if explicitly set to None
return num_experts or 0

def get_layers_start_end_indices(
self, parallel_config: ParallelConfig
) -> tuple[int, int]:
from vllm.distributed.utils import get_pp_indices

def get_total_num_hidden_layers(self) -> int:
if (
self.hf_text_config.model_type == "deepseek_mtp"
or self.hf_config.model_type == "mimo_mtp"
Expand All @@ -1393,6 +1389,15 @@ def get_layers_start_end_indices(
total_num_hidden_layers = getattr(
self.hf_text_config, "num_hidden_layers", 0
)
return total_num_hidden_layers

def get_layers_start_end_indices(
self, parallel_config: ParallelConfig
) -> tuple[int, int]:
from vllm.distributed.utils import get_pp_indices

total_num_hidden_layers = self.get_total_num_hidden_layers()

# the layout order is: DP x PP x TP
pp_rank = (
parallel_config.rank // parallel_config.tensor_parallel_size
Expand Down