[CI] Key scheduled CUDA suites by runner_config instead of hand-written jobs (#34186)

2026-08-09 16:44:53 -07:00
parent 4a5d7d3c67
commit 7c90840bad
94 changed files with 531 additions and 869 deletions
@@ -50,8 +50,8 @@ python3 test/registered/jit/test_add_constant.py
 python3 test/run_suite.py --hw cpu --suite base-a-test-cpu
 python3 test/run_suite.py --hw cuda --suite base-a-test-1-gpu-small

-# Nightly tests
-python3 test/run_suite.py --hw cuda --suite nightly-1-gpu --nightly
+# Nightly tests (CUDA nightly suites take no --nightly; the stage is in the name)
+python3 test/run_suite.py --hw cuda --suite nightly-test-1-gpu-large

 # With auto-partitioning (for parallel CI jobs)
 python3 test/run_suite.py --hw cuda --suite base-b-test-1-gpu-small \
@@ -12,7 +12,7 @@ from sglang.test.test_utils import (
    popen_launch_server,
 )

-register_cuda_ci(est_time=810, suite="nightly-4-gpu-b200", nightly=True)
+register_cuda_ci(est_time=1200, stage="nightly", runner_config="4-gpu-b200")

 NEMOTRON_3_SUPER_NVFP4_MODEL = "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4"

@@ -6,8 +6,9 @@ from sglang.test.performance_test_runner import PerformanceTestParams
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings

-# Runs on both H200 and B200 via nightly-8-gpu-common suite
-register_cuda_ci(est_time=1800, suite="nightly-8-gpu-common", nightly=True)
+# Runs on both H200 and B200: registered once per runner_config below
+register_cuda_ci(est_time=2880, stage="nightly", runner_config="8-gpu-h200")
+register_cuda_ci(est_time=2880, stage="nightly", runner_config="8-gpu-b200")

 GLM_52_FP8_MODEL_PATH = "zai-org/GLM-5.2-FP8"

@@ -6,8 +6,9 @@ from sglang.test.performance_test_runner import PerformanceTestParams
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings

-# Runs on both H200 and B200 via nightly-8-gpu-common suite
-register_cuda_ci(est_time=1800, suite="nightly-8-gpu-common", nightly=True)
+# Runs on both H200 and B200: registered once per runner_config below
+register_cuda_ci(est_time=1320, stage="nightly", runner_config="8-gpu-h200")
+register_cuda_ci(est_time=1320, stage="nightly", runner_config="8-gpu-b200")

 GLM_4_6_MODEL_PATH = "zai-org/GLM-4.6"

@@ -5,9 +5,10 @@ from sglang.test.performance_test_runner import PerformanceTestParams
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings

-# Runs on both H200 and B200 via nightly-8-gpu-common suite
+# Runs on both H200 and B200: registered once per runner_config below
 # Higher est_time due to 6 variants with both performance and accuracy tests
-register_cuda_ci(est_time=1800, suite="nightly-8-gpu-common", nightly=True)
+register_cuda_ci(est_time=690, stage="nightly", runner_config="8-gpu-h200")
+register_cuda_ci(est_time=690, stage="nightly", runner_config="8-gpu-b200")

 GPT_OSS_120B_MXFP4_MODEL_PATH = "openai/gpt-oss-120b"
 GPT_OSS_120B_EAGLE3_DRAFT_MODEL_PATH = "lmsys/EAGLE3-gpt-oss-120b-bf16"
@@ -10,7 +10,8 @@ from sglang.test.test_utils import ModelLaunchSettings, is_blackwell_system

 # NVFP4 needs Blackwell FP4 kernels, so this runs on the Blackwell leg of the
 # common 8-GPU suite (Hopper is skipped below).
-register_cuda_ci(est_time=3600, suite="nightly-8-gpu-common", nightly=True)
+register_cuda_ci(est_time=3600, stage="nightly", runner_config="8-gpu-h200")
+register_cuda_ci(est_time=3600, stage="nightly", runner_config="8-gpu-b200")

 INKLING_NVFP4_MODEL = "thinkingmachines/Inkling-NVFP4"
 INKLING_SMALL_NVFP4_MODEL = "thinkingmachines/Inkling-Small-NVFP4"
@@ -6,8 +6,9 @@ from sglang.test.performance_test_runner import PerformanceTestParams
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings

-# Runs on both H200 and B200 via nightly-8-gpu-common suite
-register_cuda_ci(est_time=3600, suite="nightly-8-gpu-common", nightly=True)
+# Runs on both H200 and B200: registered once per runner_config below
+register_cuda_ci(est_time=2820, stage="nightly", runner_config="8-gpu-h200")
+register_cuda_ci(est_time=2820, stage="nightly", runner_config="8-gpu-b200")

 KIMI_K25_MODEL_PATH = "moonshotai/Kimi-K2.5"

@@ -12,7 +12,8 @@ from sglang.test.ci.ci_register import register_cuda_ci
 from sglang.test.kits.eval_accuracy_kit import GSM8KMixin
 from sglang.test.server_fixtures.default_fixture import DefaultServerBase

-register_cuda_ci(est_time=600, suite="nightly-8-gpu-common", nightly=True)
+register_cuda_ci(est_time=300, stage="nightly", runner_config="8-gpu-h200")
+register_cuda_ci(est_time=300, stage="nightly", runner_config="8-gpu-b200")


 class TestLing26Flash(GSM8KMixin, DefaultServerBase):
@@ -6,8 +6,9 @@ from sglang.test.performance_test_runner import PerformanceTestParams
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings

-# Runs on both H200 and B200 via nightly-8-gpu-common suite
-register_cuda_ci(est_time=1800, suite="nightly-8-gpu-common", nightly=True)
+# Runs on both H200 and B200: registered once per runner_config below
+register_cuda_ci(est_time=1800, stage="nightly", runner_config="8-gpu-h200")
+register_cuda_ci(est_time=1800, stage="nightly", runner_config="8-gpu-b200")

 LLAMA4_MODEL_PATH = "meta-llama/Llama-4-Scout-17B-16E-Instruct"

@@ -6,7 +6,7 @@ from sglang.test.performance_test_runner import PerformanceTestParams
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings

-register_cuda_ci(est_time=1200, suite="nightly-8-gpu-h200", nightly=True)
+register_cuda_ci(est_time=1200, stage="nightly", runner_config="8-gpu-h200")

 # LongCat-Flash-Lite-FP8 is the smallest member of the LongCat family
 # (~138 GB FP8 weights, hidden=3072, 14 layers, 256 routed + 128 zero
@@ -6,8 +6,9 @@ from sglang.test.performance_test_runner import PerformanceTestParams
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings

-# Runs on both H200 and B200 via nightly-8-gpu-common suite
-register_cuda_ci(est_time=1800, suite="nightly-8-gpu-common", nightly=True)
+# Runs on both H200 and B200: registered once per runner_config below
+register_cuda_ci(est_time=1860, stage="nightly", runner_config="8-gpu-h200")
+register_cuda_ci(est_time=1860, stage="nightly", runner_config="8-gpu-b200")

 MINIMAX_M25_MODEL_PATH = "MiniMaxAI/MiniMax-M2.5"

@@ -8,9 +8,10 @@ from sglang.test.performance_test_runner import PerformanceTestParams
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings, is_blackwell_system

-# Runs on both H200 and B200 via nightly-8-gpu-common suite
+# Runs on both H200 and B200: registered once per runner_config below
 # Note: trtllm_mla backend may have hardware-specific behavior
-register_cuda_ci(est_time=3000, suite="nightly-8-gpu-common", nightly=True)
+register_cuda_ci(est_time=3000, stage="nightly", runner_config="8-gpu-h200")
+register_cuda_ci(est_time=3000, stage="nightly", runner_config="8-gpu-b200")

 MISTRAL_LARGE3_FP8_MODEL_PATH = "mistralai/Mistral-Large-3-675B-Instruct-2512"
 MISTRAL_LARGE3_NVFP4_MODEL_PATH = "mistralai/Mistral-Large-3-675B-Instruct-2512-NVFP4"
@@ -7,8 +7,9 @@ from sglang.test.performance_test_runner import PerformanceTestParams
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings, is_blackwell_system

-# Runs on both Hopper and Blackwell via nightly-8-gpu-common suite
-register_cuda_ci(est_time=5400, suite="nightly-8-gpu-common", nightly=True)
+# Runs on both Hopper and Blackwell: registered once per runner_config below
+register_cuda_ci(est_time=3360, stage="nightly", runner_config="8-gpu-h200")
+register_cuda_ci(est_time=3360, stage="nightly", runner_config="8-gpu-b200")

 NEMOTRON_3_SUPER_BF16_MODEL = "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"
 NEMOTRON_3_SUPER_NVFP4_MODEL = "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4"
@@ -6,8 +6,9 @@ from sglang.test.performance_test_runner import PerformanceTestParams
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings

-# Runs on both H200 and B200 via nightly-8-gpu-common suite
-register_cuda_ci(est_time=1800, suite="nightly-8-gpu-common", nightly=True)
+# Runs on both H200 and B200: registered once per runner_config below
+register_cuda_ci(est_time=3000, stage="nightly", runner_config="8-gpu-h200")
+register_cuda_ci(est_time=3000, stage="nightly", runner_config="8-gpu-b200")

 QWEN35_MODEL_PATH = "Qwen/Qwen3.5-397B-A17B-FP8"

@@ -5,7 +5,8 @@ from sglang.test.ci.ci_register import register_cuda_ci
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings

-register_cuda_ci(est_time=510, suite="nightly-8-gpu-common", nightly=True)
+register_cuda_ci(est_time=1680, stage="nightly", runner_config="8-gpu-h200")
+register_cuda_ci(est_time=1680, stage="nightly", runner_config="8-gpu-b200")

 RING_2_5_1T_MODEL_PATH = "inclusionAI/Ring-2.5-1T"

@@ -12,7 +12,7 @@ from sglang.test.test_deterministic_utils import (
    TestDeterministicBase,
 )

-register_cuda_ci(est_time=240, suite="nightly-1-gpu", nightly=True)
+register_cuda_ci(est_time=240, stage="nightly", runner_config="1-gpu-large")

 DEEPSEEK_MODEL = "lmsys/sglang-ci-dsv3-test"

@@ -12,7 +12,7 @@ from sglang.test.test_deterministic_utils import (
    TestDeterministicBase,
 )

-register_cuda_ci(est_time=200, suite="nightly-4-gpu", nightly=True)
+register_cuda_ci(est_time=200, stage="nightly", runner_config="4-gpu-h100")

 QWEN3_NEXT = "Qwen/Qwen3-Next-80B-A3B-Instruct"

@@ -17,7 +17,7 @@ from sglang.test.test_utils import (
    write_github_step_summary,
 )

-register_cuda_ci(est_time=450, suite="nightly-4-gpu-b200", nightly=True)
+register_cuda_ci(est_time=900, stage="nightly", runner_config="4-gpu-b200")

 FULL_DEEPSEEK_V3_FP4_MODEL_PATH = "nvidia/DeepSeek-V3-0324-FP4"
 SERVER_LAUNCH_TIMEOUT = 1000
@@ -12,7 +12,7 @@ from sglang.test.test_utils import (
    popen_launch_server,
 )

-register_cuda_ci(est_time=800, suite="nightly-4-gpu-b200", nightly=True)
+register_cuda_ci(est_time=1770, stage="nightly", runner_config="4-gpu-b200")


 class FlashinferTrtllmGenMoeBackendFP8Base:
@@ -11,7 +11,7 @@ import unittest
 from sglang.test.ci.ci_register import register_cuda_ci
 from sglang.test.server_fixtures.pcg_spec_fixture import PCGSpecBase

-register_cuda_ci(est_time=531, suite="nightly-4-gpu", nightly=True)
+register_cuda_ci(est_time=130, stage="nightly", runner_config="4-gpu-h100")


 class TestPCGWithEAGLE3(PCGSpecBase, unittest.TestCase):
@@ -15,7 +15,7 @@ from sglang.test.test_utils import (
    CustomTestCase,
 )

-register_cuda_ci(est_time=531, suite="nightly-1-gpu", nightly=True)
+register_cuda_ci(est_time=110, stage="nightly", runner_config="1-gpu-large")


 class TestPCGWithDFlash(PCGSpecBase, CustomTestCase):
@@ -8,7 +8,7 @@ import unittest
 from sglang.test.ci.ci_register import register_cuda_ci
 from sglang.test.server_fixtures.pcg_spec_fixture import PCGSpecBase

-register_cuda_ci(est_time=531, suite="nightly-4-gpu", nightly=True)
+register_cuda_ci(est_time=450, stage="nightly", runner_config="4-gpu-h100")


 class TestPCGWithMTP(PCGSpecBase, unittest.TestCase):
@@ -19,7 +19,7 @@ from sglang.test.test_utils import (
 )

 # CI Registration
-register_cuda_ci(est_time=180, suite="nightly-1-gpu", nightly=True)
+register_cuda_ci(est_time=250, stage="nightly", runner_config="1-gpu-large")
 register_amd_ci(est_time=180, suite="stage-b-test-1-gpu-large-amd")


@@ -20,7 +20,7 @@ register_amd_ci(
    suite="nightly-amd-accuracy-8-gpu-mi35x-qwen35-triton-dcp",
    nightly=True,
 )
-register_cuda_ci(est_time=4800, suite="nightly-4-gpu-b200", nightly=True)
+register_cuda_ci(est_time=4800, stage="nightly", runner_config="4-gpu-b200")

 QWEN35_MODEL_PATH = os.environ.get("QWEN3_5_MODEL_PATH", "Qwen/Qwen3.5-397B-A17B-FP8")
 SERVER_LAUNCH_TIMEOUT = 4800
@@ -21,7 +21,7 @@ from sglang.test.test_utils import (
    popen_launch_server,
 )

-register_cuda_ci(est_time=40, suite="nightly-1-gpu", nightly=True)
+register_cuda_ci(est_time=70, stage="nightly", runner_config="1-gpu-large")
 register_amd_ci(est_time=40, suite="nightly-amd-1-gpu", nightly=True)
 register_cpu_ci(est_time=225, suite="base-c-test-cpu")

@@ -50,7 +50,7 @@ from sglang.test.test_utils import (
    run_distributed_test,
 )

-register_cuda_ci(est_time=30, suite="nightly-2-gpu", nightly=True)
+register_cuda_ci(est_time=30, stage="nightly", runner_config="2-gpu-large")
 register_amd_ci(est_time=60, suite="nightly-amd", nightly=True)


@@ -35,7 +35,7 @@ from sglang.test.test_utils import (
    popen_launch_server,
 )

-register_cuda_ci(est_time=300, suite="nightly-4-gpu", nightly=True)
+register_cuda_ci(est_time=290, stage="nightly", runner_config="4-gpu-h100")
 register_amd_ci(
    est_time=300,
    suite="nightly-amd-4-gpu",
@@ -9,6 +9,8 @@ Env knobs:
  SGLANG_PRECISION_COMMIT         override sglang sha (7-40 hex) tagged on push
  SGLANG_PRECISION_HF_REPO        required HF dataset repo for cross-runner
                                  baseline storage; see precision_baseline_store
+  SGLANG_PRECISION_HF_TOKEN       write token for that repo (not HF_TOKEN, which
+                                  carries the runner's gated-model read token)
 """

 from __future__ import annotations
@@ -47,7 +49,7 @@ try:
 except Exception:  # pragma: no cover
    _hfs = None

-register_cuda_ci(est_time=3600, suite="nightly-precision-8-gpu-h200", nightly=True)
+register_cuda_ci(est_time=3600, stage="nightly", runner_config="8-gpu-h200")

 DEFAULT_MODELS_FOR_NIGHTLY_PRECISION = "zai-org/GLM-5.2-FP8"
 DEFAULT_DIFF_THRESHOLD = 1e-3
@@ -17,7 +17,7 @@ from sglang.test.test_utils import (
    popen_launch_server,
 )

-register_cuda_ci(est_time=120, suite="nightly-1-gpu", nightly=True)
+register_cuda_ci(est_time=240, stage="nightly", runner_config="1-gpu-large")
 register_amd_ci(est_time=120, suite="nightly-amd-1-gpu", nightly=True)
 register_cpu_ci(est_time=622, suite="base-c-test-cpu")

@@ -19,7 +19,7 @@ from sglang.test.test_utils import (
    popen_launch_server,
 )

-register_cuda_ci(est_time=1200, suite="nightly-8-gpu-b200", nightly=True)
+register_cuda_ci(est_time=450, stage="nightly", runner_config="8-gpu-b200")

 KIMI_LINEAR_MODEL = "moonshotai/Kimi-Linear-48B-A3B-Instruct"
 PHYSICAL_PAGE_SIZE = 64
@@ -23,7 +23,7 @@ from sglang.test.test_utils import (
    try_cached_model,
 )

-register_cuda_ci(est_time=420, suite="nightly-eval-text-2-gpu", nightly=True)
+register_cuda_ci(est_time=200, stage="nightly", runner_config="2-gpu-large")

 # 72 routed experts + 48 replicas = 120 physical, 60 per rank, so two thirds of
 # the routed (token, expert) pairs get double-counted when ranks disagree. At 24
@@ -23,7 +23,7 @@ from sglang.test.test_utils import (
 # downloading on cache miss. Use a longer timeout than the default 600s.
 NIGHTLY_EVAL_SERVER_TIMEOUT = 1800

-register_cuda_ci(est_time=3600, suite="nightly-eval-text-2-gpu", nightly=True)
+register_cuda_ci(est_time=2880, stage="nightly", runner_config="2-gpu-large")

 MODEL_SCORE_THRESHOLDS = {
    # sgl-eval (zero-shot chat, \boxed{}, math_verify grading). Thresholds are
@@ -19,7 +19,7 @@ from sglang.test.test_utils import (
 # Use a longer timeout than the default 600s.
 NIGHTLY_EVAL_SERVER_TIMEOUT = 1800

-register_cuda_ci(est_time=7200, suite="nightly-eval-vlm-2-gpu", nightly=True)
+register_cuda_ci(est_time=7200, stage="nightly", runner_config="2-gpu-large")

 MODEL_THRESHOLDS = {
    # Conservative thresholds on 100 MMMU samples, especially for latency thresholds
@@ -6,9 +6,7 @@ from sglang.test.performance_test_runner import PerformanceTestParams
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings

-register_cuda_ci(
-    est_time=7200, suite="nightly-4-gpu-gb300-deepseek-v4-pro-fp4", nightly=True
-)
+register_cuda_ci(est_time=7200, stage="nightly", runner_config="4-gpu-gb300")

 MODEL_PATH = "deepseek-ai/DeepSeek-V4-Pro"
 SERVER_LAUNCH_TIMEOUT = 3600
@@ -6,7 +6,7 @@ from sglang.test.performance_test_runner import PerformanceTestParams
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings

-register_cuda_ci(est_time=7200, suite="nightly-4-gpu-gb300-glm5-nvfp4", nightly=True)
+register_cuda_ci(est_time=2280, stage="nightly", runner_config="4-gpu-gb300")

 MODEL_PATH = "nvidia/GLM-5.2-NVFP4"

@@ -6,9 +6,7 @@ from sglang.test.performance_test_runner import PerformanceTestParams
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings

-register_cuda_ci(
-    est_time=7200, suite="nightly-4-gpu-gb300-kimi-k25-nvfp4", nightly=True
-)
+register_cuda_ci(est_time=7200, stage="nightly", runner_config="4-gpu-gb300")

 MODEL_PATH = "nvidia/Kimi-K2.5-NVFP4"
 DRAFT_MODEL_PATH = "lightseekorg/kimi-k2.5-eagle3-mla"
@@ -6,7 +6,7 @@ from sglang.test.performance_test_runner import PerformanceTestParams
 from sglang.test.run_combined_tests import run_combined_tests
 from sglang.test.test_utils import ModelLaunchSettings

-register_cuda_ci(est_time=7200, suite="nightly-4-gpu-gb300-qwen35-fp8", nightly=True)
+register_cuda_ci(est_time=7200, stage="nightly", runner_config="4-gpu-gb300")

 MODEL_PATH = "Qwen/Qwen3.5-397B-A17B-FP8"

@@ -25,7 +25,7 @@ from sglang.kernels.ops.kv_canary.verify import VerifyPlan
 from sglang.kernels.ops.kv_canary.write import WritePlan
 from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci

-register_cuda_ci(est_time=900, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=40, stage="nightly", runner_config="1-gpu-large")
 # AMD mirrors the CUDA nightly registration (nightly-only, no per-PR suite).
 register_amd_ci(est_time=900, suite="nightly-amd-kernel-1-gpu", nightly=True)

@@ -16,7 +16,7 @@ from sglang.kernels.ops.kv_canary.scatter_req_token_ids import (
 )
 from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci

-register_cuda_ci(est_time=180, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=20, stage="nightly", runner_config="1-gpu-large")
 # AMD mirrors the CUDA nightly registration (nightly-only, no per-PR suite).
 # Note: amd_ci_exec.sh sets SGLANG_IS_IN_CI, so this runs the CI-reduced range
 # (_BS_AXIS_CI/_SEQ_LEN_AXIS_CI via get_benchmark_range), same as CUDA nightly.
@@ -32,7 +32,7 @@ from sglang.kernels.ops.kv_canary.verify import (
 )
 from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci

-register_cuda_ci(est_time=900, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=20, stage="nightly", runner_config="1-gpu-large")
 # AMD mirrors the CUDA nightly registration (nightly-only, no per-PR suite).
 # Note: amd_ci_exec.sh sets SGLANG_IS_IN_CI, so this runs the CI-reduced range
 # (build_fast_matrix_cases via get_benchmark_range), same as CUDA nightly.
@@ -30,7 +30,7 @@ from sglang.kernels.ops.kv_canary.verify import (
 from sglang.kernels.ops.kv_canary.write import WritePlan, launch_canary_write_kernel
 from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci

-register_cuda_ci(est_time=900, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=20, stage="nightly", runner_config="1-gpu-large")
 # AMD mirrors the CUDA nightly registration (nightly-only, no per-PR suite).
 # Note: amd_ci_exec.sh sets SGLANG_IS_IN_CI, so this runs the CI-reduced range
 # (build_fast_matrix_cases via get_benchmark_range), same as CUDA nightly.
@@ -14,7 +14,7 @@ from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci

 register_cuda_ci(est_time=20, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=30, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=20, stage="nightly", runner_config="1-gpu-large")
 register_amd_ci(est_time=20, stage="jit-kernel-unit", runner_config="amd")


@@ -14,7 +14,7 @@ from sglang.srt.layers.attention.dsa.utils import (
 from sglang.srt.utils import is_sm100_supported
 from sglang.test.ci.ci_register import register_cuda_ci

-register_cuda_ci(est_time=180, suite="nightly-4-gpu-b200", nightly=True)
+register_cuda_ci(est_time=180, stage="nightly", runner_config="4-gpu-b200")

 BLOCK_KV = 64
 HEAD_DIM = 128
@@ -17,7 +17,7 @@ from sglang.srt.layers.attention.dsa.utils import (
 from sglang.srt.utils import is_sm90_supported, is_sm100_supported
 from sglang.test.ci.ci_register import register_cuda_ci

-register_cuda_ci(est_time=40, suite="nightly-4-gpu-b200", nightly=True)
+register_cuda_ci(est_time=40, stage="nightly", runner_config="4-gpu-b200")

 BLOCK_KV = 64
 HEAD_DIM = 128
@@ -10,7 +10,7 @@ from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci

 register_cuda_ci(est_time=64, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=256, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=390, stage="nightly", runner_config="1-gpu-large")
 register_amd_ci(est_time=64, suite="jit-kernel-unit-test-amd")

 DEVICE = "cuda"
@@ -46,11 +46,7 @@ register_cuda_ci(
    runner_config="8-gpu-h200",
 )
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(
-    est_time=300,
-    suite="nightly-kernel-8-gpu-h200",
-    nightly=True,
-)
+register_cuda_ci(est_time=110, stage="nightly", runner_config="8-gpu-h200")

 # ---------------------------------------------------------------------------
 # Test parameters
@@ -36,7 +36,7 @@ from sglang.test.kernels.utils import multigpu_pytest_main

 register_cuda_ci(est_time=240, stage="extra-b", runner_config="8-gpu-h200")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=240, suite="nightly-kernel-8-gpu-h200", nightly=True)
+register_cuda_ci(est_time=70, stage="nightly", runner_config="8-gpu-h200")

 # ---------------------------------------------------------------------------
 # Test parameters
@@ -10,7 +10,7 @@ from sglang.test.ci.ci_register import register_cuda_ci

 register_cuda_ci(est_time=44, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=176, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=220, stage="nightly", runner_config="1-gpu-large")

 DEVICE = "cuda"
 DTYPE = torch.bfloat16
@@ -14,7 +14,7 @@ from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci

 register_cuda_ci(est_time=15, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=120, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=30, stage="nightly", runner_config="1-gpu-large")
 register_amd_ci(est_time=30, suite="nightly-amd-kernel-1-gpu", nightly=True)

 DEVICE = "cuda"
@@ -18,7 +18,7 @@ from sglang.test.ci.ci_register import register_cuda_ci

 register_cuda_ci(est_time=16, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=120, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=20, stage="nightly", runner_config="1-gpu-large")

 CORRECTNESS_BATCH_SIZES = get_ci_test_range(
    [1, 2, 8, 128, 256, 512, 1536, 2048, 4096, 11008, 16384],
@@ -17,7 +17,7 @@ from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci

 register_cuda_ci(est_time=10, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=60, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=20, stage="nightly", runner_config="1-gpu-large")
 register_amd_ci(est_time=15, suite="nightly-amd-kernel-1-gpu", nightly=True)

 DEVICE = "cuda"
@@ -31,7 +31,7 @@ from sglang.test.ci.ci_register import register_cuda_ci

 register_cuda_ci(est_time=15, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=60, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=20, stage="nightly", runner_config="1-gpu-large")

 DEVICE = "cuda"
 DTYPES = get_ci_test_range([torch.bfloat16, torch.float16], [torch.bfloat16])
@@ -16,7 +16,7 @@ from sglang.test.ci.ci_register import register_cuda_ci

 register_cuda_ci(est_time=37, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=148, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=110, stage="nightly", runner_config="1-gpu-large")

 HIDDEN_DIMS = [1024, 4096, 5120, 6144, 7168]
 ROUTER_GEMM_CASES = get_ci_test_range(
@@ -24,7 +24,7 @@ from sglang.test.ci.ci_register import register_cuda_ci
 from sglang.test.kernels.utils import multigpu_pytest_main

 register_cuda_ci(est_time=240, stage="base-c", runner_config="4-gpu-b200")
-register_cuda_ci(est_time=480, suite="nightly-8-gpu-b200", nightly=True)
+register_cuda_ci(est_time=480, stage="nightly", runner_config="8-gpu-b200")

 _HIDDEN_SIZE = 7168
 _GEMM_AR_K_TOTAL = 12288
@@ -10,7 +10,7 @@ from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci

 register_cuda_ci(est_time=28, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=120, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=40, stage="nightly", runner_config="1-gpu-large")
 register_amd_ci(est_time=55, stage="jit-kernel-unit", runner_config="amd")

 BS_LIST = [2**n for n in range(0, 15)]
@@ -9,7 +9,7 @@ from sglang.test.ci.ci_register import register_cuda_ci

 register_cuda_ci(est_time=10, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=120, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=20, stage="nightly", runner_config="1-gpu-large")


 def sglang_jit_fused_add_rmsnorm(
@@ -10,7 +10,7 @@ from sglang.test.ci.ci_register import register_cuda_ci

 register_cuda_ci(est_time=37, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=148, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=130, stage="nightly", runner_config="1-gpu-large")


 def sglang_aot_qknorm(
@@ -10,7 +10,7 @@ from sglang.test.ci.ci_register import register_cuda_ci

 register_cuda_ci(est_time=15, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=120, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=20, stage="nightly", runner_config="1-gpu-large")


 def sglang_jit_qknorm_across_heads(
@@ -10,7 +10,7 @@ from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci

 register_cuda_ci(est_time=45, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=240, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=160, stage="nightly", runner_config="1-gpu-large")
 register_amd_ci(est_time=45, suite="jit-kernel-unit-test-amd")


@@ -15,7 +15,7 @@ from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci

 register_cuda_ci(est_time=30, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=120, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=100, stage="nightly", runner_config="1-gpu-large")
 register_amd_ci(est_time=30, stage="jit-kernel-unit", runner_config="amd")

 EPS = 1e-5
@@ -16,7 +16,7 @@ from sglang.test.quant_ref_utils import (
    dequantize_nvfp4_to_dtype,
 )

-register_cuda_ci(est_time=300, suite="nightly-4-gpu-b200", nightly=True)
+register_cuda_ci(est_time=300, stage="nightly", runner_config="4-gpu-b200")

 if torch.cuda.get_device_capability() < (10, 0):
    pytest.skip(
@@ -7,7 +7,7 @@ from sglang.srt.layers.moe.topk import biased_grouped_topk_gpu, biased_grouped_t
 from sglang.srt.utils import get_device
 from sglang.test.ci.ci_register import register_cuda_ci

-register_cuda_ci(est_time=2, suite="nightly-1-gpu", nightly=True)
+register_cuda_ci(est_time=40, stage="nightly", runner_config="1-gpu-large")


@pytest.mark.parametrize(
@@ -12,7 +12,7 @@ from sglang.test.ci.ci_register import register_cuda_ci

 register_cuda_ci(est_time=28, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=120, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=50, stage="nightly", runner_config="1-gpu-large")


 def ceil_div(a, b):
@@ -13,7 +13,7 @@ from sglang.test.ci.ci_register import register_cuda_ci

 register_cuda_ci(est_time=16, stage="base-b-kernel-unit", runner_config="1-gpu-large")
 # Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
-register_cuda_ci(est_time=120, suite="nightly-kernel-1-gpu", nightly=True)
+register_cuda_ci(est_time=20, stage="nightly", runner_config="1-gpu-large")

 try:
    from sglang.srt.utils import is_hip
@@ -34,10 +34,7 @@ import sglang as sgl
 from sglang.test.ci.ci_register import register_cuda_ci
 from sglang.test.test_utils import CustomTestCase

-register_cuda_ci(
-    est_time=300,
-    suite="nightly-8-gpu-b200",
-)
+register_cuda_ci(est_time=1800, stage="nightly", runner_config="8-gpu-b200")

 BASE_MODEL = "deepseek-ai/DeepSeek-V3.1-Base"
 LORA_HF_REPO = "yushengsu/lora-diff-DeepSeek-V3.1-Base"
@@ -27,7 +27,7 @@ from sglang.test.ci.ci_register import (
    register_xpu_ci,
 )

-register_cuda_ci(est_time=200, suite="nightly-1-gpu", nightly=True)
+register_cuda_ci(est_time=10, stage="nightly", runner_config="1-gpu-large")
 register_amd_ci(est_time=200, suite="nightly-amd-1-gpu", nightly=True)
 register_cpu_ci(est_time=6, suite="base-c-test-cpu")
 register_xpu_ci(est_time=10, suite="stage-a-test-1-gpu-xpu")
@@ -34,10 +34,7 @@ import sglang as sgl
 from sglang.test.ci.ci_register import register_cuda_ci
 from sglang.test.test_utils import CustomTestCase

-register_cuda_ci(
-    est_time=360,
-    suite="nightly-8-gpu-b200",
-)
+register_cuda_ci(est_time=420, stage="nightly", runner_config="8-gpu-b200")

 BASE_MODEL = "moonshotai/Kimi-K2.5"
 LORA_HF_REPO = "yushengsu/lora-diff-Kimi-K2.5"
@@ -27,7 +27,7 @@ from sglang.test.test_utils import (
    popen_launch_server,
 )

-register_cuda_ci(est_time=150, suite="nightly-1-gpu", nightly=True)
+register_cuda_ci(est_time=180, stage="nightly", runner_config="1-gpu-large")
 register_amd_ci(est_time=150, suite="nightly-amd-1-gpu", nightly=True)


@@ -4,7 +4,7 @@ import sglang as sgl
 from sglang.test.ci.ci_register import register_cuda_ci
 from sglang.test.test_utils import CustomTestCase

-register_cuda_ci(est_time=300, suite="nightly-4-gpu")
+register_cuda_ci(est_time=300, stage="nightly", runner_config="4-gpu-h100")

 PROMPTS = [
    "Hello, my name is",
@@ -5,7 +5,7 @@ from sglang.srt.utils.common import temp_set_env
 from sglang.test.ci.ci_register import register_cuda_ci
 from sglang.test.test_utils import CustomTestCase

-register_cuda_ci(est_time=380, suite="nightly-1-gpu", nightly=True)
+register_cuda_ci(est_time=50, stage="nightly", runner_config="1-gpu-large")

 TEST_GCS_MODEL = "gs://vertex-model-garden-public-us/codegemma/codegemma-2b/"

@@ -20,11 +20,7 @@ from sglang.test.server_fixtures.disaggregation_fixture import (
    PDDisaggregationServerBase,
 )

-register_cuda_ci(
-    est_time=450,
-    suite="nightly-8-gpu-b200",
-    nightly=True,
-)
+register_cuda_ci(est_time=750, stage="nightly", runner_config="8-gpu-b200")


 class TestGLM52DSACacheLayerSplit(PDDisaggregationServerBase, GSM8KMixin):
@@ -32,7 +32,7 @@ from sglang.test.kits.eval_accuracy_kit import GSM8KMixin
 from sglang.test.kits.prefix_cache_branching_kit import PrefixCacheBranchingMixin
 from sglang.test.server_fixtures.default_fixture import DefaultServerBase

-register_cuda_ci(est_time=600, suite="nightly-4-gpu", nightly=True)
+register_cuda_ci(est_time=570, stage="nightly", runner_config="4-gpu-h100")

 KIMI_LINEAR_MODEL = "moonshotai/Kimi-Linear-48B-A3B-Instruct"

@@ -17,7 +17,7 @@ from sglang.test.test_utils import (

 # 60 test classes testing hybrid parallelism configurations
 # Each test launches server + runs MMLU eval (~90s per test)
-register_cuda_ci(est_time=5400, suite="weekly-8-gpu-h200", nightly=True)
+register_cuda_ci(est_time=8160, stage="weekly", runner_config="8-gpu-h200")


 class Test00(CustomTestCase):
@@ -9,7 +9,7 @@ from sglang.test.test_utils import (
    parse_models,
 )

-register_cuda_ci(est_time=3600, suite="nightly-perf-text-2-gpu", nightly=True)
+register_cuda_ci(est_time=450, stage="nightly", runner_config="2-gpu-large")

 RESULT_DIR = "performance_results_text_models"

@@ -11,7 +11,7 @@ from sglang.test.test_utils import (
    parse_models,
 )

-register_cuda_ci(est_time=7200, suite="nightly-perf-vlm-2-gpu", nightly=True)
+register_cuda_ci(est_time=750, stage="nightly", runner_config="2-gpu-large")

 RESULT_DIR = "performance_results_vlms"

@@ -23,7 +23,7 @@ MIMO_LAUNCH_TIMEOUT = 3600

 # MiMo V2.5 is pre-cached on the eight-H200 runner. The H200-only nightly suite
 # exercises the asymmetric MHA host pool end to end without adding PR CI cost.
-register_cuda_ci(est_time=1200, suite="nightly-8-gpu-h200", nightly=True)
+register_cuda_ci(est_time=270, stage="nightly", runner_config="8-gpu-h200")


 class TestUnifiedMiMoHiCacheLoadBackKL(CustomTestCase):
@@ -26,7 +26,7 @@ from sglang.test.test_utils import (
 GLM5_MODEL = "zai-org/GLM-5.2-FP8"
 GLM5_LAUNCH_TIMEOUT = 3600

-register_cuda_ci(est_time=900, suite="nightly-8-gpu-h200", nightly=True)
+register_cuda_ci(est_time=690, stage="nightly", runner_config="8-gpu-h200")


 class AccuracyTwoPassMixin:
@@ -34,7 +34,7 @@ from sglang.test.test_utils import (
    popen_launch_server,
 )

-register_cuda_ci(est_time=150, suite="nightly-1-gpu", nightly=True)
+register_cuda_ci(est_time=60, stage="nightly", runner_config="1-gpu-large")

 _MODEL_NAME = "Qwen/Qwen3-0.6B"
 # We address the up half via the HF-style unfused name "up_proj.weight". sglang's
@@ -20,7 +20,7 @@ from sglang.test.test_utils import (
    popen_launch_server,
 )

-register_cuda_ci(est_time=120, suite="nightly-1-gpu", nightly=True)
+register_cuda_ci(est_time=50, stage="nightly", runner_config="1-gpu-large")
 register_amd_ci(est_time=120, suite="nightly-amd-1-gpu", nightly=True)
 register_cpu_ci(est_time=184, suite="base-c-test-cpu")

@@ -11,7 +11,7 @@ from sglang.test.test_utils import CustomTestCase

 # Note: MI300 (gfx942) has 64KB shared memory limit but kernel needs 66KB
 # MI35x (gfx950/CDNA4) may have different limits - testing on MI35x only
-register_cuda_ci(est_time=10, suite="nightly-1-gpu", nightly=True)
+register_cuda_ci(est_time=20, stage="nightly", runner_config="1-gpu-large")
 register_amd_ci(est_time=10, suite="nightly-amd-1-gpu-mi35x", nightly=True)

 device_type = getattr(torch.accelerator.current_accelerator(), "type", "cpu")
@@ -7,7 +7,7 @@ from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
 from sglang.test.kits.mmmu_vlm_kit import MMMUMultiModelTestBase
 from sglang.test.test_utils import is_in_ci

-register_cuda_ci(est_time=500, suite="nightly-4-gpu", nightly=True)
+register_cuda_ci(est_time=510, stage="nightly", runner_config="4-gpu-h100")
 register_amd_ci(est_time=500, suite="nightly-amd-4-gpu", nightly=True)

 MODELS = [
@@ -121,34 +121,16 @@ PER_COMMIT_SUITES = {
 # Nightly test suites (run nightly, organized by GPU configuration)
 NIGHTLY_SUITES = {
    HWBackend.CUDA: [
-        "nightly-1-gpu",
-        "nightly-2-gpu",
-        "nightly-4-gpu",
-        "nightly-4-gpu-b200",
-        "nightly-8-gpu",
-        "nightly-8-gpu-h200",
-        "nightly-8-gpu-h20",
-        "nightly-8-gpu-b200",
-        "nightly-8-gpu-h200-basic",  # Basic tests for large models on H200
-        "nightly-8-gpu-b200-basic",  # Basic tests for large models on B200
-        "nightly-8-gpu-common",  # Common tests that run on both H200 and B200
-        "nightly-kernel-1-gpu",
-        "nightly-kernel-8-gpu-h200",
-        # Eval and perf suites (2-gpu)
-        "nightly-eval-text-2-gpu",
-        "nightly-eval-vlm-2-gpu",
-        "nightly-perf-text-2-gpu",
-        "nightly-perf-vlm-2-gpu",
-        # GB300 (4x GB300 NVL4) nightly suites
-        "nightly-4-gpu-gb300",
-        "nightly-4-gpu-gb300-deepseek-v4-pro-fp4",
-        "nightly-4-gpu-gb300-glm5-nvfp4",
-        "nightly-4-gpu-gb300-kimi-k25",
-        "nightly-4-gpu-gb300-kimi-k25-nvfp4",
-        "nightly-4-gpu-gb300-qwen35-fp8",
-        "nightly-4-gpu-gb300-qwen35-nvfp4",
-        # Nightly precision regression (per-layer hidden state comparison)
-        "nightly-precision-8-gpu-h200",
+        # `stage="nightly"` + a runner_config, same `{stage}-test-{runner_config}`
+        # shape as the per-commit suites. No `nightly=True`: the stage name
+        # carries the cadence; only the legacy suites below still need the flag.
+        "nightly-test-1-gpu-large",
+        "nightly-test-2-gpu-large",
+        "nightly-test-4-gpu-h100",
+        "nightly-test-4-gpu-b200",
+        "nightly-test-4-gpu-gb300",
+        "nightly-test-8-gpu-h200",
+        "nightly-test-8-gpu-b200",
    ],
    HWBackend.AMD: [
        "nightly-amd",
@@ -194,7 +176,9 @@ OTHER_SUITES = {
    ],
    HWBackend.CUDA: [
        "stress",
-        "weekly-8-gpu-h200",
+        # `stage="weekly"` -- same shape. The three dicts group names for
+        # readability only; validation reads their union.
+        "weekly-test-8-gpu-h200",
    ],
 }

@@ -244,14 +228,10 @@ def filter_tests(
        if t.backend == hw and t.effective_suite == suite and t.nightly == nightly
    ]

-    valid_suites = (
-        NIGHTLY_SUITES.get(hw, []) if nightly else PER_COMMIT_SUITES.get(hw, [])
-    )
-
-    if suite not in valid_suites:
-        print(
-            f"Warning: Unknown suite {suite} for backend {hw.name}, nightly={nightly}"
-        )
+    # Union of all three dicts, not just the per-commit or nightly half:
+    # CUDA nightly suites are selected by name alone, without --nightly.
+    if suite not in _valid_suites_by_backend().get(hw, set()):
+        print(f"Warning: Unknown suite {suite} for backend {hw.name}")

    enabled_tests = [t for t in ci_tests if t.disabled is None]
    skipped_tests = [t for t in ci_tests if t.disabled is not None]
@@ -369,9 +349,11 @@ def run_a_suite(args):

    pretty_print_tests(args, ci_tests, skipped_tests)

+    # None hands the per-file budget over to est_time (see run_unittest_files).
+    timeout = None if args.timeout_from_est_time else args.timeout_per_file
+
    # Add extra timeout when retry is enabled
-    timeout = args.timeout_per_file
-    if args.enable_retry:
+    if timeout is not None and args.enable_retry:
        timeout += args.retry_timeout_increase

    return run_unittest_files(
@@ -399,7 +381,10 @@ def main():
    parser.add_argument(
        "--nightly",
        action="store_true",
-        help="Run nightly tests instead of per-commit tests.",
+        help=(
+            "Include tests registered with nightly=True (AMD/CPU/NPU). CUDA "
+            "scheduled suites are selected by name and take no flag."
+        ),
    )
    parser.add_argument(
        "--timeout-per-file",
@@ -407,6 +392,14 @@ def main():
        default=1200,
        help="The time limit for running one file in seconds (default: 1200).",
    )
+    parser.add_argument(
+        "--timeout-from-est-time",
+        action="store_true",
+        help=(
+            "Derive each file's time limit from its own est_time instead of "
+            "the flat --timeout-per-file, for suites mixing fast and slow tests."
+        ),
+    )
    parser.add_argument(
        "--continue-on-error",
        action="store_true",