Skip to content

[Bugfix][Model] Fix baichuan model loader for tp #18597

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 1 commit into from
May 23, 2025
+7 −4
Merged

[Bugfix][Model] Fix baichuan model loader for tp #18597

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
11 changes: 7 additions & 4 deletions vllm/model_executor/models/baichuan.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,8 @@
from vllm.model_executor.layers.rotary_embedding import get_rope
from vllm.model_executor.layers.vocab_parallel_embedding import (
ParallelLMHead, VocabParallelEmbedding)
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from vllm.model_executor.model_loader.weight_utils import (
default_weight_loader, row_parallel_weight_loader)
from vllm.model_executor.sampling_metadata import SamplingMetadata
from vllm.sequence import IntermediateTensors

Expand Down Expand Up @@ -384,7 +385,7 @@ def __init__(
lora_config = vllm_config.lora_config
self.config = config
self.lora_config = lora_config

self.tp_size = get_tensor_model_parallel_world_size()
self.quant_config = quant_config
self.model = BaiChuanModel(vllm_config=vllm_config,
prefix=prefix,
Expand Down Expand Up @@ -438,8 +439,10 @@ def lm_head_weight_loader(self, param: nn.Parameter,
is_baichuan2 = self.config.vocab_size == 125696
if is_baichuan2:
loaded_weight = torch.nn.functional.normalize(loaded_weight)

default_weight_loader(param, loaded_weight)
if self.tp_size > 1:
row_parallel_weight_loader(param, loaded_weight)
else:
default_weight_loader(param, loaded_weight)


class BaichuanForCausalLM(BaiChuanBaseForCausalLM):
Expand Down