[Core] Integrate TrackingArgumentParser (#3369)

Signed-off-by: Alex Brooks <albrooks@redhat.com>
This commit is contained in:
Alex Brooks authored and GitHub committed 2026-06-02 21:56:24 +08:00
1 parent bd37f3c27d
commit 12e75c6618
43 files changed
+885 -1262

No files matched your search

@@ -10,7 +10,6 @@ import soundfile as sf
from vllm import SamplingParams
from vllm.multimodal.media.audio import load_audio
from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
from vllm_omni.entrypoints.omni import Omni
from vllm_omni.model_executor.models.cosyvoice3.tokenizer import get_qwen_tokenizer
from vllm_omni.model_executor.models.cosyvoice3.utils import extract_text_token
@@ -65,7 +64,6 @@ def run_e2e():
required=True,
help="Path to tokenizer directory (e.g., <model_path>/CosyVoice-BlankEN).",
)
nullify_stage_engine_defaults(parser)
args = parser.parse_args()
# Ensure tokenizer directory exists
if not os.path.exists(args.tokenizer):
@@ -26,16 +26,14 @@ import torch
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
from vllm.utils.argparse_utils import FlexibleArgumentParser
from vllm_omni import AsyncOmni, Omni
from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
from vllm_omni.model_executor.models.fish_speech.dac_utils import DAC_HOP_LENGTH, DAC_SAMPLE_RATE
from vllm_omni.model_executor.models.fish_speech.prompt_utils import (
build_fish_text_only_prompt_ids,
estimate_fish_voice_clone_prompt_len_from_normalized,
normalize_fish_voice_clone_texts,
)
from vllm_omni.utils.tracking_parser import TrackingArgumentParser
logger = logging.getLogger(__name__)
@@ -211,7 +209,7 @@ async def main_streaming(args):
def parse_args():
parser = FlexibleArgumentParser(
parser = TrackingArgumentParser(
description="Fish Speech S2 Pro offline inference with vLLM Omni",
)
parser.add_argument(
@@ -267,7 +265,6 @@ def parse_args():
default=False,
help="Stream audio chunks as they arrive via AsyncOmni.",
)
nullify_stage_engine_defaults(parser)
return parser.parse_args()
@@ -30,10 +30,9 @@ from pathlib import Path
import numpy as np
import soundfile as sf
import torch
from vllm.utils.argparse_utils import FlexibleArgumentParser
from vllm_omni import Omni
from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
from vllm_omni.utils.tracking_parser import TrackingArgumentParser
SAMPLE_RATE = 24_000
DEFAULT_TEXTS = (
@@ -43,7 +42,7 @@ DEFAULT_TEXTS = (
def parse_args():
parser = FlexibleArgumentParser(description="Offline higgs-audio v2 inference")
parser = TrackingArgumentParser(description="Offline higgs-audio v2 inference")
parser.add_argument(
"--model",
type=str,
@@ -88,7 +87,6 @@ def parse_args():
default=None,
help="Transcript of the reference clip. Required when --ref-audio is set.",
)
nullify_stage_engine_defaults(parser)
return parser.parse_args()
@@ -5,11 +5,11 @@ from typing import Any
import soundfile as sf
import torch
from vllm.utils.argparse_utils import FlexibleArgumentParser
from vllm_omni.utils.tracking_parser import TrackingArgumentParser
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
from vllm_omni.entrypoints.omni import Omni
from vllm_omni.inputs.data import OmniTokensPrompt
from vllm_omni.model_executor.models.ming_flash_omni.prompt_utils import (
@@ -68,7 +68,7 @@ def save_audio(mm: dict[str, Any], output_path: str) -> None:
def parse_args():
parser = FlexibleArgumentParser(description="Ming-flash-omni standalone talker offline e2e example")
parser = TrackingArgumentParser(description="Ming-flash-omni standalone talker offline e2e example")
parser.add_argument("--model", type=str, default=MODEL_NAME, help="Model name or local path.")
parser.add_argument(
"--deploy-config",
@@ -89,7 +89,6 @@ def parse_args():
parser.add_argument("--init-timeout", type=int, default=600, help="Engine init timeout in seconds.")
parser.add_argument("--stage-init-timeout", type=int, default=300, help="Single stage init timeout in seconds.")
nullify_stage_engine_defaults(parser)
return parser.parse_args()
@@ -38,7 +38,8 @@ from pathlib import Path
import soundfile as sf
import torch
from vllm import SamplingParams
from vllm.utils.argparse_utils import FlexibleArgumentParser
from vllm_omni.utils.tracking_parser import TrackingArgumentParser
# Prevent multiprocessing from re-importing CUDA in the wrong context.
os.environ.setdefault("VLLM_WORKER_MULTIPROC_METHOD", "spawn")
@@ -155,7 +156,7 @@ def main(args) -> None:
def parse_args():
parser = FlexibleArgumentParser(description="MOSS-TTS-Nano offline inference")
parser = TrackingArgumentParser(description="MOSS-TTS-Nano offline inference")
parser.add_argument("--text", default="Hello, this is MOSS-TTS-Nano speaking.", help="Text to synthesize.")
parser.add_argument(
"--ref-audio",
@@ -21,7 +21,6 @@ import os
import numpy as np
import soundfile as sf
from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
from vllm_omni.entrypoints.omni import Omni
from vllm_omni.inputs.data import OmniDiffusionSamplingParams
@@ -86,7 +85,6 @@ def run_e2e():
default=None,
help="Random seed for generation",
)
nullify_stage_engine_defaults(parser)
args = parser.parse_args()
if not os.path.exists(args.stage_config):
@@ -15,10 +15,8 @@ import torch
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
from vllm.utils.argparse_utils import FlexibleArgumentParser
from vllm_omni import AsyncOmni, Omni
from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
from vllm_omni.utils.tracking_parser import TrackingArgumentParser
logger = logging.getLogger(__name__)
@@ -435,7 +433,7 @@ async def main_streaming(args):
def parse_args():
parser = FlexibleArgumentParser(description="Demo on using vLLM for offline inference with audio language models")
parser = TrackingArgumentParser(description="Demo on using vLLM for offline inference with audio language models")
parser.add_argument(
"--query-type",
"-q",
@@ -548,7 +546,6 @@ def parse_args():
help="Number of prompts per batch (default: 1, sequential).",
)
nullify_stage_engine_defaults(parser)
return parser.parse_args()
@@ -12,17 +12,16 @@ from pathlib import Path
import soundfile as sf
import torch
from vllm.utils.argparse_utils import FlexibleArgumentParser
from vllm_omni import Omni
from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
from vllm_omni.utils.tracking_parser import TrackingArgumentParser
REPO_ROOT = Path(__file__).resolve().parents[4]
SAMPLE_RATE = 48_000
def parse_args():
parser = FlexibleArgumentParser(description="Offline VoxCPM2 native AR inference")
parser = TrackingArgumentParser(description="Offline VoxCPM2 native AR inference")
parser.add_argument(
"--model",
type=str,
@@ -60,7 +59,6 @@ def parse_args():
default=None,
help="Optional transcript of --ref-audio (enables continuation mode).",
)
nullify_stage_engine_defaults(parser)
return parser.parse_args()
@@ -27,11 +27,10 @@ except ImportError:
"pip install -e ."
)
from vllm import SamplingParams
from vllm.utils.argparse_utils import FlexibleArgumentParser
from vllm_omni import AsyncOmni
from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
from vllm_omni.entrypoints.omni import Omni
from vllm_omni.utils.tracking_parser import TrackingArgumentParser
logger = logging.getLogger(__name__)
@@ -230,7 +229,7 @@ def run_non_streaming(inputs, sampling_params_list, model_name, args, output_dir
def parse_args() -> Namespace:
parser = FlexibleArgumentParser(description="Demo on using vLLM for offline inference with Voxtral TTS")
parser = TrackingArgumentParser(description="Demo on using vLLM for offline inference with Voxtral TTS")
parser.add_argument(
"--model",
type=str,
@@ -313,7 +312,6 @@ def parse_args() -> Namespace:
default=None,
help="Quantization method (e.g. 'fp8'). Applied to the language model only.",
)
nullify_stage_engine_defaults(parser)
return parser.parse_args()