diff --git a/.github/workflows/pr-test.yml b/.github/workflows/pr-test.yml index 23d777c43..a3d30324c 100644 --- a/.github/workflows/pr-test.yml +++ b/.github/workflows/pr-test.yml @@ -84,7 +84,7 @@ jobs: timeout-minutes: 25 run: | cd test/srt - python3 run_suite.py --suite minimal --range-begin 14 --range-end 21 + python3 run_suite.py --suite minimal --range-begin 14 --range-end 23 unit-test-backend-part-4: if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request' @@ -101,7 +101,7 @@ jobs: timeout-minutes: 25 run: | cd test/srt - python3 run_suite.py --suite minimal --range-begin 21 + python3 run_suite.py --suite minimal --range-begin 23 unit-test-backend-2-gpu-part-1: if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request' diff --git a/test/srt/Llama-3.1-8B-Instruct.json b/test/srt/double-sparsity-config-Llama-3.1-8B-Instruct.json similarity index 100% rename from test/srt/Llama-3.1-8B-Instruct.json rename to test/srt/double-sparsity-config-Llama-3.1-8B-Instruct.json diff --git a/test/srt/test_double_sparsity.py b/test/srt/test_double_sparsity.py index 1a35280a0..20896aff2 100644 --- a/test/srt/test_double_sparsity.py +++ b/test/srt/test_double_sparsity.py @@ -18,7 +18,9 @@ class TestDoubleSparsity(unittest.TestCase): cls.model = DEFAULT_MODEL_NAME_FOR_TEST cls.base_url = DEFAULT_URL_FOR_TEST dirpath = os.path.dirname(__file__) - config_file = os.path.join(dirpath, "Llama-3.1-8B-Instruct.json") + config_file = os.path.join( + dirpath, "double-sparsity-config-Llama-3.1-8B-Instruct.json" + ) # NOTE: Generate the config file by running https://github.com/andy-yang-1/DoubleSparse/blob/main/evaluation/group_channel_config.py cls.process = popen_launch_server( cls.model,