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

Jump to bottom

Llama3 mlp data parallel #16910

Draft
wants to merge 4 commits into
base: mbezulj/feature/llama3_data_parallel
Choose a base branch
from
Draft

Llama3 mlp data parallel #16910

wants to merge 4 commits into from

Conversation

mbezuljTT
Copy link
Contributor

@mbezuljTT mbezuljTT commented Jan 20, 2025 •
edited
Loading

pytest models/demos/llama3/tests/test_llama_mlp.py local runs:

N300

PASSED models/demos/llama3/tests/test_llama_mlp.py::test_llama_mlp_inference[wormhole_b0-True-batch_1_dp_1_tp_2-seq_len_65536_-mesh_device0]
PASSED models/demos/llama3/tests/test_llama_mlp.py::test_llama_mlp_inference[wormhole_b0-True-batch_1_dp_1_tp_2-seq_len_32768_-mesh_device0]
PASSED models/demos/llama3/tests/test_llama_mlp.py::test_llama_mlp_inference[wormhole_b0-True-batch_1_dp_1_tp_2-seq_len_32_-mesh_device0]
PASSED models/demos/llama3/tests/test_llama_mlp.py::test_llama_mlp_inference[wormhole_b0-True-batch_2_dp_2_tp_1-seq_len_65536_-mesh_device0]
PASSED models/demos/llama3/tests/test_llama_mlp.py::test_llama_mlp_inference[wormhole_b0-True-batch_2_dp_2_tp_1-seq_len_32768_-mesh_device0]
PASSED models/demos/llama3/tests/test_llama_mlp.py::test_llama_mlp_inference[wormhole_b0-True-batch_2_dp_2_tp_1-seq_len_32_-mesh_device0]
SKIPPED [3] models/demos/llama3/tests/test_llama_mlp.py:54: Skipping test, selected tensor parallel 8 doesn't match device size 2
SKIPPED [3] models/demos/llama3/tests/test_llama_mlp.py:54: Skipping test, selected data parallel 8 doesn't match device size 2

T3K

PASSED models/demos/llama3/tests/test_llama_mlp.py::test_llama_mlp_inference[wormhole_b0-True-batch_1_dp_1_tp_8-seq_len_65536_-mesh_device0]
PASSED models/demos/llama3/tests/test_llama_mlp.py::test_llama_mlp_inference[wormhole_b0-True-batch_1_dp_1_tp_8-seq_len_32768_-mesh_device0]
PASSED models/demos/llama3/tests/test_llama_mlp.py::test_llama_mlp_inference[wormhole_b0-True-batch_1_dp_1_tp_8-seq_len_32_-mesh_device0]
PASSED models/demos/llama3/tests/test_llama_mlp.py::test_llama_mlp_inference[wormhole_b0-True-batch_8_dp_8_tp_1-seq_len_65536_-mesh_device0]
PASSED models/demos/llama3/tests/test_llama_mlp.py::test_llama_mlp_inference[wormhole_b0-True-batch_8_dp_8_tp_1-seq_len_32768_-mesh_device0]
PASSED models/demos/llama3/tests/test_llama_mlp.py::test_llama_mlp_inference[wormhole_b0-True-batch_8_dp_8_tp_1-seq_len_32_-mesh_device0]
SKIPPED [3] models/demos/llama3/tests/test_llama_mlp.py:54: Skipping test, selected tensor parallel 2 doesn't match device size 8

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@mbezuljTT