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

fix(ci): update est_time for 57 tests based on runtime analysis (#21896)

Browse Source 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Liangsheng Yin
2026-04-01 20:16:13 -07:00
committed by GitHub
co-authored by Claude Opus 4.6
parent 2ef12073f4
commit 875a615993
57 changed files with 61 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files
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=132, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=15, suite="stage-b-test-1-gpu-large")
class TestFP8Base(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=520, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=80, suite="stage-b-test-1-gpu-large")
class TestFP8KVCacheTritonBackend(CustomTestCase):
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=8, suite="stage-b-test-1-gpu-small")
register_cuda_ci(est_time=16, 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_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=5, suite="stage-a-test-cpu")
register_cpu_ci(est_time=20, 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=185, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=370, suite="stage-b-test-1-gpu-large")
MODEL_SCORE_THRESHOLDS = {
"hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4": 0.825,
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=103, suite="stage-b-test-1-gpu-small")
register_cuda_ci(est_time=200, 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