[CI] Move some Lora/Deterministic CI tests to nightly (#12507)

test/srt/run_suite.py

@@ -25,12 +25,8 @@ suites = {
         TestFile("layers/attention/mamba/test_mamba_ssm_ssd.py", 20),
         TestFile("lora/test_lora.py", 150),
         TestFile("lora/test_lora_eviction.py", 240),
-        TestFile("lora/test_lora_eviction_policy.py", 200),
-        TestFile("lora/test_lora_backend.py", 99),
-        TestFile("lora/test_lora_qwen3.py", 97),
-        TestFile("lora/test_lora_radix_cache.py", 200),
-        TestFile("lora/test_lora_openai_api.py", 30),
         TestFile("lora/test_lora_update.py", 600),
+        TestFile("lora/test_lora_backend.py", 99),
         TestFile("lora/test_multi_lora_backend.py", 60),
         TestFile("models/test_compressed_tensors_models.py", 42),
         TestFile("models/test_cross_encoder_models.py", 100),
@@ -39,7 +35,6 @@ suites = {
         TestFile("models/test_generation_models.py", 103),
         TestFile("models/test_nvidia_nemotron_nano_v2.py", 160),
         TestFile("models/test_qwen_models.py", 82),
-        TestFile("batch_invariant/test_batch_invariant_ops.py", 10),
         TestFile("models/test_reward_models.py", 132),
         TestFile("models/test_transformers_models.py", 320),
         TestFile("models/test_vlm_models.py", 741),
@@ -55,7 +50,6 @@ suites = {
         TestFile("openai_server/features/test_openai_server_ebnf.py", 20),
         TestFile("openai_server/features/test_openai_server_hidden_states.py", 240),
         TestFile("openai_server/features/test_reasoning_content.py", 89),
-        TestFile("openai_server/features/test_lora_openai_compatible.py", 150),
         TestFile("openai_server/function_call/test_openai_function_calling.py", 60),
         TestFile("openai_server/function_call/test_tool_choice.py", 120),
         TestFile("openai_server/validation/test_large_max_new_tokens.py", 41),
@@ -75,7 +69,6 @@ suites = {
         TestFile("test_build_eagle_tree.py", 8),
         TestFile("test_chunked_prefill.py", 410),
         TestFile("test_create_kvindices.py", 2),
-        TestFile("test_deepseek_v3_deterministic.py", 240),
         TestFile("test_deterministic.py", 320),
         TestFile("test_eagle_infer_a.py", 370),
         TestFile("test_eagle_infer_b.py", 500),
@@ -171,7 +164,6 @@ suites = {
         TestFile("test_pp_single_node.py", 481),
     ],
     "per-commit-8-gpu-h200": [
-        TestFile("lora/test_lora_llama4.py", 400),
         TestFile("test_deepseek_v3_basic.py", 275),
         TestFile("test_deepseek_v3_mtp.py", 275),
         TestFile("test_disaggregation_hybrid_attention.py", 200),
@@ -210,7 +202,15 @@ suites = {
         TestFile("test_gguf.py", 96),
     ],
     # If the test cases take too long, considering adding them to nightly tests instead of per-commit tests
-    "nightly-1-gpu": [],
+    "nightly-1-gpu": [
+        TestFile("lora/test_lora_qwen3.py", 97),
+        TestFile("lora/test_lora_radix_cache.py", 200),
+        TestFile("lora/test_lora_eviction_policy.py", 200),
+        TestFile("lora/test_lora_openai_api.py", 30),
+        TestFile("openai_server/features/test_lora_openai_compatible.py", 150),
+        TestFile("batch_invariant/test_batch_invariant_ops.py", 10),
+        TestFile("test_deepseek_v3_deterministic.py", 240),
+    ],
     "nightly-8-gpu": [],
 }