Skip to content

reduce ds-inference log verbosity #2111

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
jeffra merged 7 commits into from
Jul 20, 2022
Merged

reduce ds-inference log verbosity #2111

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
5d104f2
reduce ds-inference log verbosity
jeffra Jul 19, 2022
c3ad1f8
reduce quantize logs
jeffra Jul 19, 2022
fcbb319
print config for only one layer and formatting fixes
jeffra Jul 19, 2022
92ff91e
remove groups log
jeffra Jul 19, 2022
1526d5a
Merge branch 'master' into jeffra/inference-logging
jeffra Jul 19, 2022
622bcb8
add missing import
jeffra Jul 19, 2022
43febb9
Merge branch 'master' into jeffra/inference-logging
jeffra Jul 20, 2022
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
4 changes: 3 additions & 1 deletion deepspeed/ops/transformer/inference/transformer_inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@
from ... import op_builder
import torch.nn as nn
from deepspeed import comm as dist
from deepspeed.utils.logging import log_dist

# Cuda modules will be imported if needed
inference_cuda_module = None
minus_inf = -10000.0
Expand Down Expand Up @@ -768,7 +770,7 @@ def __init__(self,
builder = op_builder.InferenceBuilder()
inference_cuda_module = builder.load()

print("DeepSpeed Transformer Inference config is ", self.config.__dict__)
log_dist(f"DeepSpeed-Inference config: {self.config.__dict__}", [0])

self.attention = DeepSpeedSelfAttention(self.config,
mp_group,
Expand Down