[Docs][CI] doc update & L4 example test for text-to-image page (#1910)

Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
This commit is contained in:
Zeyu Huang | 黃澤宇 authored and GitHub committed 2026-03-23 16:26:54 +08:00
1 parent 602f831068
commit 8a58394379
14 files changed
+875 -224

No files matched your search

Whitespace-only changes.
@@ -1,5 +1,6 @@
"""
Example online tests for Qwen2.5-Omni-7B model.
Online serving tests: Qwen2.5-Omni-7B.
See examples/online_serving/qwen2_5_omni/README.md
"""
import os
@@ -8,15 +9,16 @@ from vllm_omni.platforms import current_omni_platform
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
import re
import subprocess
from pathlib import Path
import pytest
from tests.conftest import OmniServerParams, convert_audio_file_to_text, cosine_similarity_text
from tests.examples.conftest import extract_content_after_keyword, run_cmd
from tests.utils import hardware_test
pytestmark = [pytest.mark.advanced_model, pytest.mark.example]
models = ["Qwen/Qwen2.5-Omni-7B"]
@@ -36,30 +38,6 @@ test_params = [
]
def run_cmd(command):
result = subprocess.run(
command,
capture_output=True,
text=True,
)
if result.returncode != 0:
print(f"STDERR: {result.stderr}")
raise subprocess.CalledProcessError(result.returncode, command)
all_output = result.stdout
print(f"All output:\n{all_output}")
return all_output
def extract_content_after_keyword(keywords, text):
matches = re.findall(rf"{keywords}\s*(.+)", text, re.DOTALL)
if not matches:
raise AssertionError(f"Keywords {keywords} not found in provided text output")
return matches[0]
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})
@@ -1,5 +1,6 @@
"""
Example Online tests for Qwen3-Omni model.
Online serving tests: Qwen3-Omni.
See examples/online_serving/qwen3_omni/README.md
"""
import os
@@ -8,15 +9,16 @@ from vllm_omni.platforms import current_omni_platform
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
import re
import subprocess
from pathlib import Path
import pytest
from tests.conftest import OmniServerParams, convert_audio_file_to_text, cosine_similarity_text
from tests.examples.conftest import extract_content_after_keyword, run_cmd
from tests.utils import hardware_test
pytestmark = [pytest.mark.advanced_model, pytest.mark.example]
models = ["Qwen/Qwen3-Omni-30B-A3B-Instruct"]
@@ -35,30 +37,6 @@ test_params = [
]
def run_cmd(command):
result = subprocess.run(
command,
capture_output=True,
text=True,
)
if result.returncode != 0:
print(f"STDERR: {result.stderr}")
raise subprocess.CalledProcessError(result.returncode, command)
all_output = result.stdout
print(f"All output:\n{all_output}")
return all_output
def extract_content_after_keyword(keywords, text):
matches = re.findall(rf"{keywords}\s*(.+)", text, re.DOTALL)
if not matches:
raise AssertionError(f"Keywords {keywords} not found in provided text output")
return matches[0]
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100", "rocm": "MI325"}, num_cards=2)
@@ -0,0 +1,136 @@
"""
Online serving tests: text-to-image.
See examples/online_serving/text_to_image/README.md
The output materials are organized in a three-level directory structure:
- Set at init: `self.output_root` for all tests (from env OUTPUT_DIR)
- Set at `self.run(...)`: `output_subfolder` for a specific example page (e.g., `example_offline_t2i`)
- Generated by `extract_readme_snippets`: `snippet.test_id` for a specific code block (matching H2 titles, e.g., `basic_usage_001`)
"""
import sys
from pathlib import Path
import pytest
from tests.conftest import OmniServer, OmniServerParams, assert_image_valid
from tests.examples.conftest import EXAMPLES, OUTPUT_DIR, run_cmd, write_zimage_lora
from tests.utils import hardware_marks
pytestmark = [pytest.mark.advanced_model, pytest.mark.example, *hardware_marks(res={"cuda": "H100"})]
T2I_ONLINE_CLIENT = EXAMPLES / "online_serving" / "text_to_image" / "openai_chat_client.py"
EXAMPLE_OUTPUT_SUBFOLDER = "example_online_t2i"
@pytest.fixture(scope="module")
def example_output_dir() -> Path:
d = OUTPUT_DIR / EXAMPLE_OUTPUT_SUBFOLDER
d.mkdir(parents=True, exist_ok=True)
return d
# Ensuring two indirect parametrization receive exactly the same parameter list.
# Then, only one omni_server instance is started for all test functions using this param set.
# Two additional pre-requisites:
# - omni_server must (and indeed is) defined as a module-scoped fixture
# - test functions sharing the same param set must be adjacent to each other
qwen_image_server_params = [OmniServerParams(model="Qwen/Qwen-Image")]
z_image_turbo_server_params = [OmniServerParams(model="Tongyi-MAI/Z-Image-Turbo")]
# --- ### Method 1: Using curl ---
@pytest.mark.parametrize("omni_server", qwen_image_server_params, indirect=True)
def test_api_calls_001(omni_server: OmniServer, example_output_dir: Path):
url = f"http://{omni_server.host}:{omni_server.port}/v1/chat/completions"
case_dir = example_output_dir / "api_calls-001"
case_dir.mkdir(parents=True, exist_ok=True)
out = case_dir / "api_calls_001.png"
json_str = """{
"messages": [
{"role": "user", "content": "A beautiful landscape painting"}
],
"extra_body": {
"height": 1024,
"width": 1024,
"num_inference_steps": 50,
"true_cfg_scale": 4.0,
"seed": 42
}
}"""
run_cmd(
f"curl -s '{url}'"
" -H 'Content-Type: application/json'"
f" -d '{json_str}'"
" | jq -r '.choices[0].message.content[0].image_url.url'"
f" | cut -d',' -f2- | base64 -d > '{out}'",
shell=True,
)
assert_image_valid(out, width=1024, height=1024)
# --- ### Method 2: Using Python Client ---
@pytest.mark.parametrize("omni_server", qwen_image_server_params, indirect=True)
def test_api_calls_002(omni_server: OmniServer, example_output_dir: Path):
case_dir = example_output_dir / "api_calls-002"
case_dir.mkdir(parents=True, exist_ok=True)
out = case_dir / "api_calls_002.png"
run_cmd(
[
sys.executable,
str(T2I_ONLINE_CLIENT),
"--prompt",
"A beautiful landscape painting",
"--output",
str(out),
"--server",
f"http://{omni_server.host}:{omni_server.port}",
]
)
assert_image_valid(out)
@pytest.mark.skip("README section 'Method 3: Using Gradio Demo' is intentionally excluded for examples tests")
def test_api_calls_003(): ...
# --- ### Using Python Client with LoRA ---
@pytest.mark.parametrize("omni_server", z_image_turbo_server_params, indirect=True)
def test_lora_001(omni_server: OmniServer, example_output_dir: Path, tmp_path: Path):
lora_dir = tmp_path / "zimage_lora_a"
write_zimage_lora(lora_dir, v_scale=8.0)
case_dir = example_output_dir / "lora-001"
case_dir.mkdir(parents=True, exist_ok=True)
out = case_dir / "lora_001.png"
run_cmd(
[
sys.executable,
str(T2I_ONLINE_CLIENT),
"--prompt",
"A piece of cheesecake",
"--lora-path",
str(lora_dir),
"--lora-name",
"a",
"--lora-scale",
"1.0",
"--output",
str(out),
"--server",
f"http://{omni_server.host}:{omni_server.port}",
]
)
assert_image_valid(out)
# --- ### Using curl with LoRA (Images API) ---
@pytest.mark.skip(reason="Covered by tests/e2e/online_serving/test_images_generations_lora.py")
def test_lora_002(): ...