Add back data parallelism (#1635)

2024-10-11 07:22:48 -07:00
parent 5d09ca5735
commit 23cc66f7b6
7 changed files with 228 additions and 39 deletions
--- a/.github/workflows/pr-test.yml
+++ b/.github/workflows/pr-test.yml
@@ -255,12 +255,11 @@ jobs:
          python3 test_mla.py
          python3 test_mla_fp8.py

-      # Temporarily disabled
-      #- name: Evaluate Data Parallelism Accuracy (TP=2)
-      #  timeout-minutes: 10
-      #  run: |
-      #    cd test/srt
-      #    python3 test_data_parallelism.py
+      - name: Evaluate Data Parallelism Accuracy (DP=2)
+        timeout-minutes: 10
+        run: |
+          cd test/srt
+          python3 test_data_parallelism.py

  finish:
    needs: [