Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
build-small-hackathon
/
mumbai-local
like
7
Paused
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
mumbai-local
/
frontend
/
server
49.8 kB
Ctrl+K
Ctrl+K
1 contributor
History:
11 commits
geekwrestler
GPU tuning: @spaces.GPU duration 90->60, max_new_tokens 768->320, remove diagnostic logging
4a9c11e
verified
27 days ago
__init__.py
571 Bytes
Deploy Mumbai Local Panic β Nemotron(ZeroGPU) dispatcher + VoxCPM2 voice
27 days ago
api_routes.py
3.78 kB
Part 2: @app.api game endpoints + @gradio/client frontend (ZeroGPU auth-forwarded GPU calls)
27 days ago
app.py
10.1 kB
Part 2: @app.api game endpoints + @gradio/client frontend (ZeroGPU auth-forwarded GPU calls)
27 days ago
gpu_llm.py
6.98 kB
GPU tuning: @spaces.GPU duration 90->60, max_new_tokens 768->320, remove diagnostic logging
27 days ago
render_state.py
5.3 kB
Deploy Mumbai Local Panic β Nemotron(ZeroGPU) dispatcher + VoxCPM2 voice
27 days ago
session.py
7.44 kB
Deploy Mumbai Local Panic β Nemotron(ZeroGPU) dispatcher + VoxCPM2 voice
27 days ago
test_server.py
12.8 kB
Deploy Mumbai Local Panic β Nemotron(ZeroGPU) dispatcher + VoxCPM2 voice
27 days ago
tts.py
2.84 kB
Warm VoxCPM2 at startup (under ZeroGPU emulation) + load_denoiser=False β fixes lazy-import CUDA-init error
27 days ago