minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

chore: update CI test est_time values (#22565)

Browse Source 
Co-authored-by: Cheng Wan <chwan@rice.edu>
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
This commit is contained in:
sglang-bot
2026-04-10 18:15:02 -07:00
committed by GitHub
co-authored by Cheng Wan sglang-bot Cheng Wan
parent b5e4ae7b1a
commit 265696b176
250 changed files with 251 additions and 251 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/quant/test_autoround.py
+1 -1
View File
@@ -17,7 +17,7 @@ from sglang.test.test_utils import (
popen_launch_server,
)
register_cuda_ci(est_time=77, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=96, suite="stage-b-test-1-gpu-large")
class TestAutoRound(CustomTestCase):
test/registered/quant/test_awq.py
+1 -1
View File
@@ -13,7 +13,7 @@ from sglang.test.test_utils import (
popen_launch_server,
)
register_cuda_ci(est_time=260, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=209, suite="stage-b-test-1-gpu-large")
register_amd_ci(est_time=200, suite="stage-b-test-1-gpu-large-amd")
test/registered/quant/test_block_int8.py
+1 -1
View File
@@ -10,7 +10,7 @@ from sglang.srt.server_args import ServerArgs, set_global_server_args_for_schedu
from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
from sglang.test.test_utils import CustomTestCase
register_cuda_ci(est_time=44, suite="stage-b-test-1-gpu-small")
register_cuda_ci(est_time=39, suite="stage-b-test-1-gpu-small")
register_amd_ci(est_time=22, suite="stage-b-test-1-gpu-small-amd")
test/registered/quant/test_bnb.py
+1 -1
View File
@@ -22,7 +22,7 @@ from sglang.test.test_utils import (
popen_launch_server,
)
register_cuda_ci(est_time=5, suite="stage-b-test-1-gpu-small")
register_cuda_ci(est_time=6, suite="stage-b-test-1-gpu-small")
VISION_MODELS = [
"unsloth/Qwen2.5-VL-7B-Instruct-bnb-4bit",
test/registered/quant/test_deepseek_v32_fp4_4gpu.py
+1 -1
View File
@@ -13,7 +13,7 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=530, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=852, suite="stage-c-test-4-gpu-b200")
FULL_DEEPSEEK_V3_FP4_MODEL_PATH = "nvidia/DeepSeek-V3.2-NVFP4"
SERVER_LAUNCH_TIMEOUT = 1200
test/registered/quant/test_deepseek_v32_fp4_mtp_4gpu.py
+1 -1
View File
@@ -16,7 +16,7 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=610, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=1030, suite="stage-c-test-4-gpu-b200")
FULL_DEEPSEEK_V3_FP4_MODEL_PATH = "nvidia/DeepSeek-V3.2-NVFP4"
SERVER_LAUNCH_TIMEOUT = 1200
test/registered/quant/test_deepseek_v3_fp4_4gpu.py
+1 -1
View File
@@ -14,7 +14,7 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=450, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=1146, suite="stage-c-test-4-gpu-b200")
FULL_DEEPSEEK_V3_FP4_MODEL_PATH = "nvidia/DeepSeek-V3-0324-FP4"
SERVER_LAUNCH_TIMEOUT = 1200
test/registered/quant/test_eval_fp8_accuracy.py
+1 -1
View File
@@ -14,7 +14,7 @@ from sglang.test.test_utils import (
popen_launch_server,
)
register_cuda_ci(est_time=250, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=326, suite="stage-b-test-1-gpu-large")
register_amd_ci(est_time=600, suite="stage-b-test-1-gpu-small-amd")
test/registered/quant/test_fp8_blockwise_gemm.py
+1 -1
View File
@@ -12,7 +12,7 @@ from sglang.test.test_utils import (
try_cached_model,
)
register_cuda_ci(est_time=400, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=302, suite="stage-c-test-4-gpu-b200")
MODEL_PATH = "Qwen/Qwen3-4B-Instruct-2507-FP8"
MXFP8_MODEL_PATH = "zianglih/Qwen3-4B-Instruct-2507-MXFP8"
test/registered/quant/test_fp8_gemm_sm120.py
+1 -1
View File
@@ -12,7 +12,7 @@ from sglang.test.test_utils import (
try_cached_model,
)
register_cuda_ci(est_time=120, suite="stage-b-test-1-gpu-small")
register_cuda_ci(est_time=144, suite="stage-b-test-1-gpu-small")
PERTENSOR_MODEL_PATH = "nvidia/Llama-3.1-8B-Instruct-FP8"
BLOCKWISE_MODEL_PATH = "Qwen/Qwen3-4B-Instruct-2507-FP8"
test/registered/quant/test_fp8_kernel.py
+1 -1
View File
@@ -9,7 +9,7 @@ from sglang.srt.layers.quantization.fp8_kernel import (
from sglang.test.ci.ci_register import register_cuda_ci
from sglang.test.test_utils import CustomTestCase
register_cuda_ci(est_time=15, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=10, suite="stage-b-test-1-gpu-large")
class TestFP8Base(CustomTestCase):
test/registered/quant/test_fp8_utils.py
+1 -1
View File
@@ -10,7 +10,7 @@ from sglang.srt.layers.quantization.fp8_utils import (
from sglang.test.ci.ci_register import register_cuda_ci
from sglang.test.test_utils import CustomTestCase
register_cuda_ci(est_time=9, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=8, suite="stage-b-test-1-gpu-large")
class TestInverseTransformScaleUe8m0(CustomTestCase):
test/registered/quant/test_fp8kv_triton.py
+1 -1
View File
@@ -12,7 +12,7 @@ from sglang.test.test_utils import (
popen_launch_server,
)
register_cuda_ci(est_time=80, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=63, suite="stage-b-test-1-gpu-large")
class TestFP8KVCacheTritonBackend(CustomTestCase):
test/registered/quant/test_gguf.py
+1 -1
View File
@@ -6,7 +6,7 @@ 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=96, suite="stage-b-test-1-gpu-small")
register_cuda_ci(est_time=71, suite="stage-b-test-1-gpu-small")
class TestGGUF(CustomTestCase):
test/registered/quant/test_gptqmodel_dynamic.py
+1 -1
View File
@@ -14,7 +14,7 @@ from sglang.test.test_utils import (
popen_launch_server,
)
register_cuda_ci(est_time=102, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=98, suite="stage-b-test-1-gpu-large")
def check_quant_method(model_path: str, use_marlin_kernel: bool):
test/registered/quant/test_int8_kernel.py
+1 -1
View File
@@ -11,7 +11,7 @@ from sglang.srt.server_args import ServerArgs, set_global_server_args_for_schedu
from sglang.test.ci.ci_register import register_cuda_ci
from sglang.test.test_utils import CustomTestCase
register_cuda_ci(est_time=16, suite="stage-b-test-1-gpu-small")
register_cuda_ci(est_time=13, suite="stage-b-test-1-gpu-small")
def native_w8a8_per_token_matmul(A, B, As, Bs, output_dtype=torch.float16):
test/registered/quant/test_marlin_moe.py
+1 -1
View File
@@ -12,7 +12,7 @@ from sglang.test.ci.ci_register import register_cuda_ci
from sglang.test.test_marlin_utils import awq_marlin_quantize, marlin_quantize
from sglang.test.test_utils import CustomTestCase
register_cuda_ci(est_time=130, suite="stage-b-test-1-gpu-small")
register_cuda_ci(est_time=85, suite="stage-b-test-1-gpu-small")
set_global_server_args_for_scheduler(object.__new__(ServerArgs))
test/registered/quant/test_modelopt_fp8.py
+1 -1
View File
@@ -12,7 +12,7 @@ from sglang.test.test_utils import (
popen_launch_server,
)
register_cuda_ci(est_time=120, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=62, suite="stage-b-test-1-gpu-large")
class TestModeloptFP8(CustomTestCase):
test/registered/quant/test_nvfp4_gemm.py
+1 -1
View File
@@ -12,7 +12,7 @@ from sglang.test.test_utils import (
try_cached_model,
)
register_cuda_ci(est_time=300, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=322, suite="stage-c-test-4-gpu-b200")
MODEL_PATH = "nvidia/Llama-3.1-8B-Instruct-NVFP4"
test/registered/quant/test_nvfp4_gemm_sm120.py
+1 -1
View File
@@ -12,7 +12,7 @@ from sglang.test.test_utils import (
try_cached_model,
)
register_cuda_ci(est_time=90, suite="stage-b-test-1-gpu-small")
register_cuda_ci(est_time=115, suite="stage-b-test-1-gpu-small")
MODEL_PATH = "nvidia/Llama-3.1-8B-Instruct-NVFP4"
test/registered/quant/test_quant_config_parsing.py
+1 -1
View File
@@ -5,7 +5,7 @@ from sglang.srt.configs.model_config import ModelConfig
from sglang.test.ci.ci_register import register_cpu_ci
from sglang.test.test_utils import CustomTestCase
register_cpu_ci(est_time=20, suite="stage-a-test-cpu")
register_cpu_ci(est_time=12, suite="stage-a-test-cpu")
class TestQuantLogString(CustomTestCase):
test/registered/quant/test_quantization.py
+1 -1
View File
@@ -16,7 +16,7 @@ from sglang.test.test_utils import (
write_results_to_json,
)
register_cuda_ci(est_time=270, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=402, suite="stage-b-test-1-gpu-large")
MODEL_SCORE_THRESHOLDS = {
# Baselines observed with gsm8k 5-shot concatenated format via chat API,
test/registered/quant/test_torchao.py
+1 -1
View File
@@ -5,7 +5,7 @@ import requests
from sglang import Engine
from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
register_cuda_ci(est_time=140, suite="stage-b-test-1-gpu-small")
register_cuda_ci(est_time=124, suite="stage-b-test-1-gpu-small")
register_amd_ci(est_time=230, suite="stage-b-test-1-gpu-small-amd")
from sglang.lang.chat_template import get_chat_template_by_model_path
from sglang.srt.utils import kill_process_tree
test/registered/quant/test_triton_scaled_mm.py
+1 -1
View File
@@ -8,7 +8,7 @@ from sglang.srt.layers.quantization.fp8_kernel import triton_scaled_mm
from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
from sglang.test.test_utils import CustomTestCase
register_cuda_ci(est_time=8, suite="stage-b-test-1-gpu-small")
register_cuda_ci(est_time=9, suite="stage-b-test-1-gpu-small")
register_amd_ci(est_time=12, suite="stage-b-test-1-gpu-small-amd")
test/registered/quant/test_w8a8_quantization.py
+1 -1
View File
@@ -14,7 +14,7 @@ from sglang.test.test_utils import (
popen_launch_server,
)
register_cuda_ci(est_time=160, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=204, suite="stage-b-test-1-gpu-large")
class BaseW8A8Test(CustomTestCase):