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

Auto TP Tutorial with T5 Example #2962

Merged
merged 10 commits into from
Apr 25, 2023
Merged

Auto TP Tutorial with T5 Example #2962

Changes from 1 commit
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
5b41f42
Update tutorial with t5 example instead of opt
molly-smith Mar 7, 2023
7151102
Revert example script changes.
molly-smith Mar 7, 2023
1931110
Add back compatible model note
molly-smith Mar 7, 2023
b7f4ec3
Merge branch 'master' into mosm/atp_tutorial_t5
molly-smith Mar 7, 2023
5f22777
Merge branch 'master' into mosm/atp_tutorial_t5
molly-smith Mar 9, 2023
d4870a5
Add opt examples for long sequences
molly-smith Mar 14, 2023
ec204f8
Add header for opt example
molly-smith Mar 14, 2023
0336518
Merge branch 'master' into mosm/atp_tutorial_t5
molly-smith Apr 21, 2023
4ffdd6a
Merge branch 'master' into mosm/atp_tutorial_t5
molly-smith Apr 25, 2023
5b71afc
Merge branch 'master' into mosm/atp_tutorial_t5
jeffra Apr 25, 2023
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
Prev Previous commit
Next Next commit
Add back compatible model note
  • Loading branch information
@molly-smith
molly-smith committed Mar 7, 2023
commit 1931110cec3d3495edc566a1897d237cee27250d
2 changes: 1 addition & 1 deletion docs/_tutorials/automatic-tensor-parallelism.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,7 @@ deepspeed --num_gpus <num_gpus> DeepSpeedExamples/inference/huggingface/text-gen
```


To enable tensor parallelism, you need to use the flag `ds_inference`:
To enable tensor parallelism, you need to use the flag `ds_inference` for the compatible models:

```bash
deepspeed --num_gpus <num_gpus> DeepSpeedExamples/inference/huggingface/text-generation/inference-test.py --name <model> --batch_size <batch_size> --test_performance --ds_inference
Expand Down