ci: unify PR test suite naming (#21187)

test/registered/lora/test_fused_moe_lora_kernel.py

@@ -14,7 +14,7 @@ from sglang.test.ci.ci_register import register_cuda_ci
 
 # ==============================================================================
 
-register_cuda_ci(est_time=120, suite="stage-b-test-large-1-gpu")
+register_cuda_ci(est_time=120, suite="stage-b-test-1-gpu-large")
 
 
 def round_up(x, base):

test/registered/lora/test_lora_backend.py

@@ -29,10 +29,10 @@ from sglang.test.lora_utils import (
 )
 from sglang.test.test_utils import CustomTestCase, is_in_ci
 
-register_cuda_ci(est_time=200, suite="stage-b-test-small-1-gpu")
+register_cuda_ci(est_time=200, suite="stage-b-test-1-gpu-small")
 register_amd_ci(
     est_time=200,
-    suite="stage-b-test-small-1-gpu-amd",
+    suite="stage-b-test-1-gpu-small-amd",
     disabled="see https://github.com/sgl-project/sglang/issues/13107",
 )
 

test/registered/lora/test_lora_eviction.py

@@ -23,8 +23,8 @@ from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
 from sglang.test.runners import SRTRunner
 from sglang.test.test_utils import CustomTestCase
 
-register_cuda_ci(est_time=224, suite="stage-b-test-small-1-gpu")
-register_amd_ci(est_time=224, suite="stage-b-test-small-1-gpu-amd")
+register_cuda_ci(est_time=224, suite="stage-b-test-1-gpu-small")
+register_amd_ci(est_time=224, suite="stage-b-test-1-gpu-small-amd")
 
 PROMPTS = [
     "AI is a field of computer science focused on",

test/registered/lora/test_lora_hf_sgl_logprob_diff.py

@@ -41,11 +41,11 @@ from sglang.test.test_utils import DEFAULT_PORT_FOR_SRT_TEST_RUNNER, CustomTestC
 
 register_cuda_ci(
     est_time=150,
-    suite="stage-b-test-small-1-gpu",
+    suite="stage-b-test-1-gpu-small",
 )
 register_amd_ci(
     est_time=250,
-    suite="stage-b-test-small-1-gpu-amd",
+    suite="stage-b-test-1-gpu-small-amd",
 )
 # Test configuration constants
 BASE_MODEL = "meta-llama/Llama-2-7b-hf"

test/registered/lora/test_lora_overlap_loading.py

@@ -29,8 +29,8 @@ from sglang.test.lora_utils import (
 )
 from sglang.test.test_utils import CustomTestCase
 
-register_cuda_ci(est_time=75, suite="stage-b-test-large-1-gpu")
-register_amd_ci(est_time=75, suite="stage-b-test-small-1-gpu-amd")
+register_cuda_ci(est_time=75, suite="stage-b-test-1-gpu-large")
+register_amd_ci(est_time=75, suite="stage-b-test-1-gpu-small-amd")
 
 
 class TestLoRAOverlapLoading(CustomTestCase):

test/registered/lora/test_lora_qwen3.py

@@ -24,7 +24,7 @@ from sglang.test.test_utils import CustomTestCase
 
 register_amd_ci(
     est_time=30,
-    suite="stage-b-test-small-1-gpu-amd",
+    suite="stage-b-test-1-gpu-small-amd",
     disabled="see https://github.com/sgl-project/sglang/issues/13107",
 )
 register_cuda_ci(est_time=97, suite="nightly-1-gpu", nightly=True)

test/registered/lora/test_lora_tp.py

@@ -31,11 +31,11 @@ from sglang.test.test_utils import CustomTestCase, is_in_ci
 
 register_cuda_ci(
     est_time=116,
-    suite="stage-b-test-large-2-gpu",
+    suite="stage-b-test-2-gpu-large",
 )
 register_amd_ci(
     est_time=116,
-    suite="stage-b-test-large-2-gpu-amd",
+    suite="stage-b-test-2-gpu-large-amd",
     disabled="see https://github.com/sgl-project/sglang/issues/13107",
 )
 

test/registered/lora/test_lora_update.py

@@ -36,7 +36,7 @@ from sglang.test.test_utils import (
 
 register_cuda_ci(
     est_time=487,
-    suite="stage-b-test-large-1-gpu",
+    suite="stage-b-test-1-gpu-large",
 )
 
 PROMPTS = [

test/registered/lora/test_multi_lora_backend.py

@@ -25,8 +25,8 @@ from sglang.test.lora_utils import (
 )
 from sglang.test.test_utils import CustomTestCase, is_in_ci
 
-register_cuda_ci(est_time=100, suite="stage-b-test-large-1-gpu")
-register_amd_ci(est_time=100, suite="stage-b-test-small-1-gpu-amd")
+register_cuda_ci(est_time=100, suite="stage-b-test-1-gpu-large")
+register_amd_ci(est_time=100, suite="stage-b-test-1-gpu-small-amd")
 
 
 class TestMultiLoRABackend(CustomTestCase):