Koko210/miku-discord
1
0
Fork 0
Code Issues 34 Pull Requests Actions Packages Projects Releases Wiki Activity

perf: reduce container sizes and build times

Browse Source 
- miku-stt: switch PyTorch CUDA -> CPU-only (~2.5 GB savings)
  - Silero VAD already runs on CPU via ONNX (onnx=True), CUDA PyTorch was waste
  - faster-whisper/CTranslate2 uses CUDA directly, no PyTorch GPU needed
  - torch+torchaudio layer: 3.3 GB -> 796 MB; total image 9+ GB -> 6.83 GB
  - Tested: Silero VAD loads (ONNX), Whisper loads on cuda, server ready

- llama-swap-rocm: add root .dockerignore to fix 31 GB build context
  - Dockerfile clones all sources from git, never COPYs from context
  - 19 GB of GGUF model files were being transferred on every build
  - Now excludes everything (*), near-zero context transfer

- anime-face-detector: add .dockerignore to exclude accumulated outputs
  - api/outputs/ (56 accumulated detection files) no longer baked into image
  - api/__pycache__/ and images/ also excluded

- .gitignore: remove .dockerignore exclusion so these files are tracked
This commit is contained in:
koko210Serve
2026-02-25 14:41:04 +02:00
parent 0edf1ef1c0
commit 9e5511da21
6 changed files with 29 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.gitignore vendored
View File

@@ -37,9 +37,6 @@ models/*.bin
*.log
logs/
# Docker
.dockerignore
# OS
.DS_Store
Thumbs.db