Unverified Commit c61a1b6f authored by Liangsheng Yin's avatar Liangsheng Yin Committed by GitHub
Browse files

Torch compile CI throughput test (#1223)

parent 9935f97b
import unittest import unittest
from types import SimpleNamespace from types import SimpleNamespace
import requests
from sglang.srt.utils import kill_child_process from sglang.srt.utils import kill_child_process
from sglang.test.run_eval import run_eval from sglang.test.run_eval import run_eval
from sglang.test.test_utils import ( from sglang.test.test_utils import (
...@@ -20,7 +22,7 @@ class TestTorchCompile(unittest.TestCase): ...@@ -20,7 +22,7 @@ class TestTorchCompile(unittest.TestCase):
cls.model, cls.model,
cls.base_url, cls.base_url,
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH, timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
other_args=["--enable-torch-compile"], other_args=["--enable-torch-compile", "--disable-radix-cache"],
) )
@classmethod @classmethod
...@@ -39,6 +41,33 @@ class TestTorchCompile(unittest.TestCase): ...@@ -39,6 +41,33 @@ class TestTorchCompile(unittest.TestCase):
metrics = run_eval(args) metrics = run_eval(args)
assert metrics["score"] >= 0.6 assert metrics["score"] >= 0.6
def run_decode(self, max_new_tokens):
response = requests.post(
self.base_url + "/generate",
json={
"text": "The capital of France is",
"sampling_params": {
"temperature": 0,
"max_new_tokens": max_new_tokens,
},
"ignore_eos": True,
},
)
return response.json()
def test_throughput(self):
import time
max_tokens = 256
tic = time.time()
res = self.run_decode(max_tokens)
tok = time.time()
print(res["text"])
throughput = max_tokens / (tok - tic)
print(f"Throughput: {throughput} tokens/s")
assert throughput >= 152
if __name__ == "__main__": if __name__ == "__main__":
unittest.main() unittest.main()
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment