Remove unused files and fix some bugs
This commit is contained in:
Gaohan123 committed
1 parent
6248bbf646
commit
6cf73c4e80
21 files changed
+548
-1891
No files matched your search
@@ -1,121 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Simple API client example for vLLM-omni server.
|
||||
|
||||
This example shows how to interact with the vLLM-omni API server
|
||||
using HTTP requests.
|
||||
"""
|
||||
|
||||
import json
|
||||
|
||||
import requests
|
||||
|
||||
|
||||
def test_health(host="localhost", port=8000):
|
||||
"""Test if the server is healthy."""
|
||||
url = f"http://{host}:{port}/health"
|
||||
try:
|
||||
response = requests.get(url, timeout=5)
|
||||
if response.status_code == 200:
|
||||
print("✅ Server is healthy")
|
||||
return True
|
||||
else:
|
||||
print(f"❌ Server health check failed: {response.status_code}")
|
||||
return False
|
||||
except requests.exceptions.RequestException as e:
|
||||
print(f"❌ Cannot connect to server: {e}")
|
||||
return False
|
||||
|
||||
|
||||
def generate_text(prompt, host="localhost", port=8000, **kwargs):
|
||||
"""Generate text using the API server."""
|
||||
url = f"http://{host}:{port}/generate"
|
||||
|
||||
# Default parameters
|
||||
params = {
|
||||
"prompts": [prompt],
|
||||
"max_tokens": kwargs.get("max_tokens", 100),
|
||||
"temperature": kwargs.get("temperature", 0.7),
|
||||
"top_p": kwargs.get("top_p", 1.0),
|
||||
"frequency_penalty": kwargs.get("frequency_penalty", 0.0),
|
||||
"presence_penalty": kwargs.get("presence_penalty", 0.0),
|
||||
}
|
||||
|
||||
# Add optional parameters
|
||||
if "stop" in kwargs:
|
||||
params["stop"] = kwargs["stop"]
|
||||
|
||||
try:
|
||||
response = requests.post(url, json=params, timeout=30)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
except requests.exceptions.RequestException as e:
|
||||
print(f"❌ API request failed: {e}")
|
||||
return None
|
||||
|
||||
|
||||
def main():
|
||||
"""Main example function."""
|
||||
print("vLLM-omni API Client Example")
|
||||
print("=" * 40)
|
||||
|
||||
# Test server health
|
||||
if not test_health():
|
||||
print("Please start the server first:")
|
||||
print(" vllm serve Qwen/Qwen3-0.6B --omni --port 8000")
|
||||
return
|
||||
|
||||
# Example 1: Simple generation
|
||||
print("\n1. Simple text generation:")
|
||||
result = generate_text("Hello, how are you?", max_tokens=50)
|
||||
if result:
|
||||
text = result["outputs"][0]["text"]
|
||||
print(" Input: Hello, how are you?")
|
||||
print(f" Output: {text}")
|
||||
|
||||
# Example 2: Creative writing
|
||||
print("\n2. Creative writing:")
|
||||
result = generate_text(
|
||||
"Write a short story about a robot learning to paint",
|
||||
max_tokens=150,
|
||||
temperature=0.9,
|
||||
)
|
||||
if result:
|
||||
text = result["outputs"][0]["text"]
|
||||
print(" Input: Write a short story about a robot learning to paint")
|
||||
print(f" Output: {text}")
|
||||
|
||||
# Example 3: Question answering
|
||||
print("\n3. Question answering:")
|
||||
result = generate_text(
|
||||
"What is the capital of France?", max_tokens=30, temperature=0.3
|
||||
)
|
||||
if result:
|
||||
text = result["outputs"][0]["text"]
|
||||
print(" Input: What is the capital of France?")
|
||||
print(f" Output: {text}")
|
||||
|
||||
# Example 4: Multiple prompts
|
||||
print("\n4. Multiple prompts:")
|
||||
prompts = ["Tell me a joke", "What's 2+2?", "Describe the color blue"]
|
||||
|
||||
for prompt in prompts:
|
||||
result = generate_text(prompt, max_tokens=30)
|
||||
if result:
|
||||
text = result["outputs"][0]["text"]
|
||||
print(f" Q: {prompt}")
|
||||
print(f" A: {text}")
|
||||
|
||||
# Example 5: Show full response structure
|
||||
print("\n5. Full response structure:")
|
||||
result = generate_text("Hello world", max_tokens=20)
|
||||
if result:
|
||||
print(" Full API response:")
|
||||
print(json.dumps(result, indent=2))
|
||||
|
||||
print("\n" + "=" * 40)
|
||||
print("API client examples completed!")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,138 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Simple vLLM-omni usage example.
|
||||
|
||||
This example demonstrates how to use vLLM-omni for basic text generation
|
||||
with a single AR (Autoregressive) stage.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
|
||||
from vllm_omni.config import create_ar_stage_config
|
||||
from vllm_omni.entrypoints.omni_llm import AsyncOmniLLM, OmniLLM
|
||||
|
||||
|
||||
def sync_example():
|
||||
"""Synchronous usage example."""
|
||||
print("=== Synchronous vLLM-omni Example ===")
|
||||
|
||||
# Create a simple AR stage configuration
|
||||
stage_config = create_ar_stage_config(
|
||||
stage_id=0,
|
||||
model_path="Qwen/Qwen3-0.6B",
|
||||
input_modalities=["text"],
|
||||
output_modalities=["text"],
|
||||
)
|
||||
|
||||
# Initialize OmniLLM
|
||||
omni_llm = OmniLLM([stage_config])
|
||||
|
||||
# Prepare stage arguments
|
||||
stage_args = [
|
||||
{
|
||||
"prompt": "Hello, how are you today?",
|
||||
"max_tokens": 50,
|
||||
"temperature": 0.7,
|
||||
}
|
||||
]
|
||||
|
||||
# Generate text
|
||||
print(f"Input: {stage_args[0]['prompt']}")
|
||||
outputs = omni_llm.generate(stage_args)
|
||||
|
||||
# Display results
|
||||
for i, output in enumerate(outputs):
|
||||
print(f"Output {i}:")
|
||||
if hasattr(output, "outputs") and output.outputs:
|
||||
for completion in output.outputs:
|
||||
print(f" Text: {completion.text}")
|
||||
print(f" Finished: {completion.finish_reason != 'length'}")
|
||||
print(f" Tokens: {len(completion.token_ids)} tokens")
|
||||
|
||||
|
||||
async def async_example():
|
||||
"""Asynchronous usage example."""
|
||||
print("\n=== Asynchronous vLLM-omni Example ===")
|
||||
|
||||
# Create a simple AR stage configuration
|
||||
stage_config = create_ar_stage_config(
|
||||
stage_id=0,
|
||||
model_path="Qwen/Qwen3-0.6B",
|
||||
input_modalities=["text"],
|
||||
output_modalities=["text"],
|
||||
)
|
||||
|
||||
# Initialize AsyncOmniLLM
|
||||
omni_llm = AsyncOmniLLM([stage_config])
|
||||
|
||||
# Prepare stage arguments
|
||||
stage_args = [
|
||||
{
|
||||
"prompt": "What is artificial intelligence?",
|
||||
"max_tokens": 100,
|
||||
"temperature": 0.8,
|
||||
}
|
||||
]
|
||||
|
||||
# Generate text asynchronously
|
||||
print(f"Input: {stage_args[0]['prompt']}")
|
||||
outputs = await omni_llm.generate_async(stage_args)
|
||||
|
||||
# Display results
|
||||
for i, output in enumerate(outputs):
|
||||
print(f"Output {i}:")
|
||||
if hasattr(output, "outputs") and output.outputs:
|
||||
for completion in output.outputs:
|
||||
print(f" Text: {completion.text}")
|
||||
print(f" Finished: {completion.finish_reason != 'length'}")
|
||||
print(f" Tokens: {len(completion.token_ids)} tokens")
|
||||
|
||||
|
||||
def multi_prompt_example():
|
||||
"""Example with multiple prompts."""
|
||||
print("\n=== Multi-Prompt Example ===")
|
||||
|
||||
# Create stage configuration
|
||||
stage_config = create_ar_stage_config(
|
||||
stage_id=0,
|
||||
model_path="Qwen/Qwen3-0.6B",
|
||||
input_modalities=["text"],
|
||||
output_modalities=["text"],
|
||||
)
|
||||
|
||||
# Initialize OmniLLM
|
||||
omni_llm = OmniLLM([stage_config])
|
||||
|
||||
# Multiple prompts
|
||||
prompts = [
|
||||
"Tell me a joke",
|
||||
"What's the weather like?",
|
||||
"Explain quantum computing",
|
||||
]
|
||||
|
||||
for prompt in prompts:
|
||||
print(f"\nInput: {prompt}")
|
||||
stage_args = [{"prompt": prompt, "max_tokens": 30, "temperature": 0.9}]
|
||||
|
||||
outputs = omni_llm.generate(stage_args)
|
||||
|
||||
if outputs and hasattr(outputs[0], "outputs") and outputs[0].outputs:
|
||||
completion = outputs[0].outputs[0]
|
||||
print(f"Output: {completion.text}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
print("vLLM-omni Simple Usage Examples")
|
||||
print("=" * 40)
|
||||
|
||||
# Run synchronous example
|
||||
sync_example()
|
||||
|
||||
# Run asynchronous example
|
||||
asyncio.run(async_example())
|
||||
|
||||
# Run multi-prompt example
|
||||
multi_prompt_example()
|
||||
|
||||
print("\n" + "=" * 40)
|
||||
print("Examples completed!")
|
||||
@@ -1,31 +0,0 @@
|
||||
# Omni Examples
|
||||
|
||||
Examples showcasing multi-stage AR + DiT pipelines powered by vLLM-omni.
|
||||
|
||||
## AR ➜ DiT with Diffusers Backend
|
||||
|
||||
```bash
|
||||
# Optional: customise models
|
||||
export AR_MODEL=Qwen/Qwen3-0.6B
|
||||
export DIT_MODEL=./models/stable-diffusion-2-1/
|
||||
|
||||
# Run with defaults (20 steps @ 512x512)
|
||||
python examples/omni/ar_dit_diffusers.py
|
||||
|
||||
# Faster run
|
||||
python examples/omni/ar_dit_diffusers.py --steps 14 --height 384 --width 384 --guidance 4.5
|
||||
```
|
||||
|
||||
Arguments:
|
||||
- `--ar-model`: Override AR stage model (default `Qwen/Qwen3-0.6B`).
|
||||
- `--dit-model`: Override DiT stage model (default env `DIT_MODEL`, else diffusers repo).
|
||||
- `--steps`: Number of diffusion steps (default 20).
|
||||
- `--guidance`: Guidance scale (default 5.0).
|
||||
- `--height` / `--width`: Output resolution (default 512).
|
||||
- `--seed`: Optional RNG seed.
|
||||
- `--prompt`, `--temperature`, `--max-tokens`: Control AR stage generation.
|
||||
- `--output`: Destination path for the generated image file.
|
||||
|
||||
Generated images are saved next to the script as `omni_dit_output.png` by default.
|
||||
|
||||
See the script for additional tweaks (scheduler, prompt chaining, etc.).
|
||||
@@ -1,175 +0,0 @@
|
||||
"""Run the AR → DiT (diffusers) pipeline using YAML configuration defaults."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import os
|
||||
from pathlib import Path
|
||||
from typing import Dict, List
|
||||
|
||||
import yaml
|
||||
|
||||
from vllm_omni import (
|
||||
DiTConfig,
|
||||
OmniLLM,
|
||||
create_ar_stage_config,
|
||||
create_dit_stage_config,
|
||||
)
|
||||
|
||||
|
||||
def parse_args() -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Run a two-stage AR → DiT pipeline with config-derived defaults."
|
||||
)
|
||||
parser.add_argument(
|
||||
"--config",
|
||||
type=Path,
|
||||
default=Path(__file__).resolve().parent / "configs" / "ar_dit_local.yaml",
|
||||
help="Path to a YAML configuration describing the pipeline stages.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--prompt",
|
||||
default="A scenic watercolor painting of a lighthouse at sunset",
|
||||
help="Prompt passed to the AR stage.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--negative-prompt",
|
||||
default=None,
|
||||
help="Optional negative prompt forwarded to the diffusion stage.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--seed",
|
||||
type=int,
|
||||
default=None,
|
||||
help="Optional seed for deterministic diffusion sampling.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--output",
|
||||
type=Path,
|
||||
default=Path("./omni_dit_output.png"),
|
||||
help="Destination path for the generated image.",
|
||||
)
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def _normalize_modalities(values: List[str] | None, default: List[str]) -> List[str]:
|
||||
if not values:
|
||||
return default
|
||||
return list(values)
|
||||
|
||||
|
||||
def _load_stage_configs_from_yaml(config_path: Path):
|
||||
with config_path.open("r", encoding="utf-8") as f:
|
||||
config = yaml.safe_load(f) or {}
|
||||
|
||||
stages = config.get("stages", [])
|
||||
if not stages:
|
||||
raise ValueError(f"No stages defined in config: {config_path}")
|
||||
|
||||
stage_configs = []
|
||||
for stage in stages:
|
||||
stage_id = stage["stage_id"]
|
||||
engine_type = stage["engine_type"]
|
||||
default_stage_args = stage.get("default_stage_args")
|
||||
|
||||
if engine_type == "AR":
|
||||
stage_configs.append(
|
||||
create_ar_stage_config(
|
||||
stage_id=stage_id,
|
||||
model_path=stage["model_path"],
|
||||
input_modalities=_normalize_modalities(
|
||||
stage.get("input_modalities"), ["text"]
|
||||
),
|
||||
output_modalities=_normalize_modalities(
|
||||
stage.get("output_modalities"), ["text"]
|
||||
),
|
||||
default_stage_args=default_stage_args,
|
||||
)
|
||||
)
|
||||
elif engine_type == "DiT":
|
||||
dit_cfg_dict: Dict = dict(stage.get("dit_config", {}))
|
||||
if "num_inference_steps" not in dit_cfg_dict:
|
||||
raise ValueError(
|
||||
"DiT stage requires 'num_inference_steps' in dit_config"
|
||||
)
|
||||
dit_cfg = DiTConfig(**dit_cfg_dict)
|
||||
|
||||
stage_configs.append(
|
||||
create_dit_stage_config(
|
||||
stage_id=stage_id,
|
||||
model_path=stage["model_path"],
|
||||
input_modalities=_normalize_modalities(
|
||||
stage.get("input_modalities"), ["text"]
|
||||
),
|
||||
output_modalities=_normalize_modalities(
|
||||
stage.get("output_modalities"), ["image"]
|
||||
),
|
||||
dit_config=dit_cfg,
|
||||
default_stage_args=default_stage_args,
|
||||
)
|
||||
)
|
||||
else:
|
||||
raise ValueError(f"Unsupported engine_type '{engine_type}' in config")
|
||||
|
||||
return stage_configs
|
||||
|
||||
|
||||
def _apply_env_overrides(stage_configs):
|
||||
ar_override = os.environ.get("AR_MODEL")
|
||||
dit_override = os.environ.get("DIT_MODEL")
|
||||
|
||||
for stage_config in stage_configs:
|
||||
if ar_override and stage_config.engine_type == "AR":
|
||||
stage_config.model_path = ar_override
|
||||
if dit_override and stage_config.engine_type == "DiT":
|
||||
stage_config.model_path = dit_override
|
||||
|
||||
|
||||
def main():
|
||||
args = parse_args()
|
||||
|
||||
stage_configs = _load_stage_configs_from_yaml(args.config)
|
||||
_apply_env_overrides(stage_configs)
|
||||
|
||||
omni = OmniLLM(stage_configs)
|
||||
|
||||
stage_overrides: Dict[int, Dict[str, object]] = {}
|
||||
if args.seed is not None or args.negative_prompt:
|
||||
for stage_config in stage_configs:
|
||||
if stage_config.engine_type != "DiT":
|
||||
continue
|
||||
override = stage_overrides.setdefault(stage_config.stage_id, {})
|
||||
if args.seed is not None:
|
||||
override["seed"] = args.seed
|
||||
if args.negative_prompt:
|
||||
override["negative_prompt"] = args.negative_prompt
|
||||
|
||||
outputs = omni.generate(
|
||||
prompt=args.prompt,
|
||||
stage_overrides=stage_overrides if stage_overrides else None,
|
||||
)
|
||||
|
||||
image = None
|
||||
for request_output in outputs:
|
||||
for completion in getattr(request_output, "outputs", []) or []:
|
||||
candidate = getattr(completion, "image", None)
|
||||
if candidate is not None:
|
||||
image = candidate
|
||||
break
|
||||
if image is not None:
|
||||
break
|
||||
|
||||
if image is None:
|
||||
print("No image found in outputs.")
|
||||
return
|
||||
|
||||
out_path = args.output.resolve()
|
||||
try:
|
||||
image.save(out_path)
|
||||
print(f"Saved image to {out_path}")
|
||||
except Exception:
|
||||
print("Generated output is not a PIL.Image; skipping save.")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,28 +0,0 @@
|
||||
# Example config for running OmniLLM with local AR + DiT models.
|
||||
stages:
|
||||
- stage_id: 0
|
||||
engine_type: AR
|
||||
model_path: Qwen/Qwen3-0.6B
|
||||
input_modalities: [text]
|
||||
output_modalities: [text]
|
||||
default_stage_args:
|
||||
max_tokens: 16
|
||||
temperature: 0.7
|
||||
- stage_id: 1
|
||||
engine_type: DiT
|
||||
model_path: stabilityai/stable-diffusion-2-1
|
||||
input_modalities: [text]
|
||||
output_modalities: [image]
|
||||
default_stage_args:
|
||||
height: 512
|
||||
width: 512
|
||||
dit_config:
|
||||
num_inference_steps: 20
|
||||
guidance_scale: 5.0
|
||||
use_diffusers: true
|
||||
diffusers_pipeline: auto
|
||||
height: 512
|
||||
width: 512
|
||||
device_config:
|
||||
device: mps
|
||||
dtype: float16
|
||||
Reference in new issue
Block a user