Online weight updates from torch.distributed (#2279)

This commit is contained in:
Chayenne
2024-12-01 23:23:18 -08:00
committed by GitHub
parent 28bc60dcab
commit 983bfcf386
12 changed files with 1120 additions and 61 deletions

View File

@@ -27,6 +27,7 @@ concurrency:
cancel-in-progress: true
jobs:
unit-test-frontend:
if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
runs-on: 1-gpu-runner
@@ -98,6 +99,11 @@ jobs:
python3 test_mla_fp8.py
python3 test_dp_attention.py
- name: Test update weights from distributed
timeout-minutes: 10
run: |
cd test/srt
python3 test_update_weights_from_distributed.py
performance-test-1-gpu-part-1:
if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
@@ -245,6 +251,7 @@ jobs:
cd test/srt
python3 test_moe_eval_accuracy_large.py
finish:
needs: [
unit-test-frontend, unit-test-backend-1-gpu, unit-test-backend-2-gpu,