Skip to content

feat(config): 在m1max 64G上成功运行需要改动的地方 #262

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
1193700079 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat(config): 在m1max 64G上成功运行需要改动的地方 #262

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 10 additions & 4 deletions config/chat_with_qwen_omni.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ default:
module: client/rtc_client/client_handler_rtc
connection_ttl: 36000
# max time a session will last for
connection_ttl: 900
# connection_ttl: 900
SileroVad:
module: vad/silerovad/vad_handler_silero
speaking_threshold: 0.5
Expand Down Expand Up @@ -52,10 +52,16 @@ default:
# force_create_avatar: false # Whether to force regenerate digital human data
# debug: false # Whether to enable debug mode
# multi_thread_inference: true # true: use 2 threads to inference (unet, vae), false: use single-thread to inference
# LiteAvatar:
# module: avatar/liteavatar/avatar_handler_liteavatar
# avatar_name: ~/.cache/modelscope/hub/models/HumanAIGC-Engineering/LiteAvatarGallery/20250408/sample_data/
# fps: 25
# debug: false
# enable_fast_mode: false
# use_gpu: false

LiteAvatar:
module: avatar/liteavatar/avatar_handler_liteavatar
avatar_name: 20250408/sample_data
fps: 25
debug: false
enable_fast_mode: false
use_gpu: true
use_gpu: false
2 changes: 0 additions & 2 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,9 +28,7 @@ dependencies = [
"tqdm~=4.67.1",
"typing-extensions~=4.12.2",
"uvicorn~=0.34.0",
"torch==2.8.0",
"torchvision",
"torchaudio",
"python-dotenv>=1.1.0",
]

Expand Down
2 changes: 1 addition & 1 deletion src/handlers/avatar/liteavatar/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,5 +13,5 @@ dependencies = [
"typeguard==2.13.3",
"vector-quantize-pytorch~=1.21.7",
"vocos~=0.1.0",
"onnxruntime-gpu~=1.20.1",
"onnxruntime~=1.20.1",
]
4 changes: 2 additions & 2 deletions src/handlers/avatar/liteavatar/shared_memory_buffer_pool.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -160,7 +160,8 @@ def _attach_audio_pool(self, shm_names: List[str]):
except Exception as e:
logger.error(f"Failed to attach to audio buffer {i} ({shm_name}): {e}")
self.audio_buffers.append(None)
logger.info(f"Audio attached: {len(self.audio_buffers)} buffers, queue: {self.audio_available.qsize()}")
qsize = self._safe_qsize(self.audio_available)
logger.info(f"Audio attached: {len(self.audio_buffers)} buffers, queue: {qsize}")

def _attach_video_pool(self, shm_names: List[str]):
"""Attach to existing video buffer pool."""
Expand Down Expand Up @@ -428,4 +429,3 @@ def __del__(self):
self.cleanup()
except Exception as e:
logger.error(f"Error in __del__: {e}")