Skip to content

fix: deepspeed import error fix in lightning_trainer #313

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

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
+24 −8
Open

fix: deepspeed import error fix in lightning_trainer #313

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
acf2ba1
fix: deepspeed import error fix in lightning_trainer
glennko Nov 22, 2025
c15ca51
Merge branch 'main' into glenn/deepspeederr
glennko Nov 22, 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
32 changes: 24 additions & 8 deletions src/xturing/trainers/lightning_trainer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,14 @@

import pytorch_lightning as pl
import torch
from deepspeed.ops.adam import DeepSpeedCPUAdam

try:
from deepspeed.ops.adam import DeepSpeedCPUAdam
except ModuleNotFoundError as import_err: # pragma: no cover - optional dependency
DeepSpeedCPUAdam = None
_DEEPSPEED_IMPORT_ERROR = import_err
else:
_DEEPSPEED_IMPORT_ERROR = None
from pytorch_lightning import callbacks
from pytorch_lightning.loggers import Logger
from pytorch_lightning.trainer.trainer import Trainer
Expand Down Expand Up @@ -51,6 +58,11 @@ def configure_optimizers(self):
self.pytorch_model.parameters(), lr=self.learning_rate
)
elif self.optimizer_name == "cpu_adam":
if DeepSpeedCPUAdam is None:
raise ModuleNotFoundError(
"DeepSpeed is required for optimizer 'cpu_adam'. "
"Install it with `pip install deepspeed`."
) from _DEEPSPEED_IMPORT_ERROR
optimizer = DeepSpeedCPUAdam(
self.pytorch_model.parameters(), lr=self.learning_rate
)
Expand Down Expand Up @@ -164,13 +176,17 @@ def __init__(
]

strategy = "auto"
if not IS_INTERACTIVE:
strategy = (
"deepspeed_stage_2_offload"
if optimizer_name == "cpu_adam"
else "deepspeed_stage_2"
)

if use_deepspeed:
if DeepSpeedCPUAdam is None:
raise ModuleNotFoundError(
"use_deepspeed=True requires DeepSpeed. Install it with `pip install deepspeed`."
) from _DEEPSPEED_IMPORT_ERROR
if not IS_INTERACTIVE:
strategy = (
"deepspeed_stage_2_offload"
if optimizer_name == "cpu_adam"
else "deepspeed_stage_2"
)
self.trainer = Trainer(
num_nodes=1,
accelerator="gpu",
Expand Down