Use only one GPU for MLA CI tests (#2858)
This commit is contained in:
8
.github/workflows/pr-test.yml
vendored
8
.github/workflows/pr-test.yml
vendored
@@ -87,18 +87,16 @@ jobs:
|
||||
run: |
|
||||
bash scripts/ci_install_dependency.sh
|
||||
|
||||
- name: Evaluate data parallelism accuracy (DP=2)
|
||||
- name: Test data parallelism (DP=2)
|
||||
timeout-minutes: 10
|
||||
run: |
|
||||
cd test/srt
|
||||
python3 test_data_parallelism.py
|
||||
|
||||
- name: Evaluate MLA accuracy (TP=2)
|
||||
- name: Test data parallelism attention (DP=2)
|
||||
timeout-minutes: 10
|
||||
run: |
|
||||
cd test/srt
|
||||
python3 test_mla.py
|
||||
python3 test_mla_fp8.py
|
||||
python3 test_dp_attention.py
|
||||
|
||||
- name: Test update weights from distributed
|
||||
@@ -107,7 +105,7 @@ jobs:
|
||||
cd test/srt
|
||||
python3 test_update_weights_from_distributed.py
|
||||
|
||||
- name: Evaluate MoE EP accuracy (TP=2)
|
||||
- name: Test expert parallelism (EP=2)
|
||||
timeout-minutes: 10
|
||||
run: |
|
||||
cd test/srt
|
||||
|
||||
Reference in New Issue
Block a user