Fix unit tests (#11503)

test/README.md

@@ -10,7 +10,7 @@ cd sglang/test/srt
 python3 test_srt_endpoint.py
 
 # Run a single test
-python3 -m unittest test_srt_endpoint.TestSRTEndpoint.test_simple_decode
+python3 test_srt_endpoint.py TestSRTEndpoint.test_simple_decode
 
 # Run a suite with multiple files
 python3 run_suite.py --suite per-commit
@@ -21,21 +21,23 @@ python3 run_suite.py --suite per-commit
 cd sglang/test/lang
 
 # Run a single file
-python3 test_srt_backend.py
+python3 test_choices.py
 ```
 
 ## Adding or Updating Tests in CI
 
 - Create new test files under `test/srt` or `test/lang` depending on the type of test.
-- Ensure they are referenced in the respective `run_suite.py` (e.g., `test/srt/run_suite.py`) so they’re picked up in CI. For most small test cases, they can be added to the `per-commit` suite. Sort the test cases alphabetically.
-- The CI will run the `per-commit` and `nightly` automatically. If you need special setup or custom test groups, you may modify the workflows in [`.github/workflows/`](https://github.com/sgl-project/sglang/tree/main/.github/workflows).
-
+- Ensure they are referenced in the respective `run_suite.py` (e.g., `test/srt/run_suite.py`) so they are picked up in CI. For most small test cases, they can be added to the `per-commit-1-gpu` suite. Sort the test cases alphabetically by name.
+- Ensure you added `unittest.main()` for unittest and `pytest.main([__file__])` for pytest in the scripts. The CI run them via `python3 test_file.py`.
+- The CI will run some suites such as `per-commit-1-gpu`, `per-commit-2-gpu`, and `nightly-1-gpu` automatically. If you need special setup or custom test groups, you may modify the workflows in [`.github/workflows/`](https://github.com/sgl-project/sglang/tree/main/.github/workflows).
 
 ## Writing Elegant Test Cases
 
-- Examine existing tests in [sglang/test](https://github.com/sgl-project/sglang/tree/main/test) for practical examples.
+- Learn from existing examples in [sglang/test/srt](https://github.com/sgl-project/sglang/tree/main/test/srt).
+- Reduce the test time by using smaller models and reusing the server for multiple test cases. Launching a server takes a lot of time.
+- Use as few GPUs as possible. Do not run long tests with 8-gpu runners.
+- If the test cases take too long, considering adding them to nightly tests instead of per-commit tests.
 - Keep each test function focused on a single scenario or piece of functionality.
 - Give tests descriptive names reflecting their purpose.
 - Use robust assertions (e.g., assert, unittest methods) to validate outcomes.
 - Clean up resources to avoid side effects and preserve test independence.
-- Reduce the test time by using smaller models and reusing the server for multiple test cases.

test/srt/run_suite.py

@@ -13,7 +13,7 @@ class TestFile:
 
 # NOTE: please sort the test cases alphabetically by the test file name
 suites = {
-    "per-commit": [
+    "per-commit-1-gpu": [
         TestFile("function_call/test_json_schema_constraint.py", 30),
         TestFile("hicache/test_hicache.py", 116),
         TestFile("hicache/test_hicache_eagle.py", 150),
@@ -179,6 +179,9 @@ suites = {
         TestFile("test_vllm_dependency.py", 185),
         # 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-8-gpu": [],
 }
 
 # Add AMD tests

test/srt/test_mla_int8_deepseek_v3.py

@@ -72,7 +72,8 @@ class TestDeepseekV3MTPChannelInt8(CustomTestCase):
                     "16",
                     "--enable-torch-compile",
                     "--torch-compile-max-bs",
-                    "2" "--speculative-algorithm",
+                    "2",
+                    "--speculative-algorithm",
                     "EAGLE",
                     "--speculative-draft-model-path",
                     "sgl-project/sglang-ci-dsv3-channel-int8-test-NextN",
@@ -177,7 +178,8 @@ class TestDeepseekV3MTPBlockInt8(CustomTestCase):
                     "16",
                     "--enable-torch-compile",
                     "--torch-compile-max-bs",
-                    "2" "--speculative-algorithm",
+                    "2",
+                    "--speculative-algorithm",
                     "EAGLE",
                     "--speculative-num-steps",
                     "2",