Skip to content
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

misc: rm unused model_loader #1110

Merged
merged 1 commit into from
Aug 15, 2024
+1 −576
Merged

misc: rm unused model_loader #1110

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
10 changes: 1 addition & 9 deletions python/sglang/srt/model_executor/model_runner.py
View file
Original file line number Diff line number Diff line change
@@ -38,6 +38,7 @@
init_distributed_environment,
initialize_model_parallel,
)
from vllm.model_executor.model_loader import get_model
from vllm.model_executor.models import ModelRegistry

from sglang.global_config import global_config
@@ -168,15 +169,6 @@ def load_model(self):
if self.model_config.model_overide_args is not None:
vllm_model_config.hf_config.update(self.model_config.model_overide_args)

if (
self.server_args.efficient_weight_load
and "llama" in self.server_args.model_path.lower()
and self.server_args.quantization == "fp8"
):
from sglang.srt.model_loader.model_loader import get_model
else:
from vllm.model_executor.model_loader import get_model

self.model = get_model(
model_config=vllm_model_config,
device_config=device_config,
292 changes: 0 additions & 292 deletions python/sglang/srt/model_loader/model_loader.py
View file

This file was deleted.

275 changes: 0 additions & 275 deletions python/sglang/srt/model_loader/utils.py
View file

This file was deleted.