LyAhn/vibepod
1
0
Fork 0
mirror of https://github.com/JezzWTF/vibepod.git synced 2026-06-13 03:58:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

perf: migrate to JezzWTF/VibeVoice fork, parallel CFG executors

Browse Source 
Switch vibevoice dependency from microsoft/VibeVoice to JezzWTF/VibeVoice
fork (commit e76701f) which contains the async decode + parallel CFG
optimisations directly in generate(). Removes the instance-method
patching approach (vibevoice_generate_patch.py deleted).

server/vibevoice_server.py:
- Add _cfg_executor (ThreadPoolExecutor, 1 worker) alongside _decode_executor
- _install_cpu_pipeline_optimizations now sets both executors directly as
  model._vibepod_decode_executor and model._vibepod_cfg_executor
- Both executors shut down in lifespan on exit
- Remove vibevoice_generate_patch import/install (no longer needed)

server/pyproject.toml:
- vibevoice source changed to git+https://github.com/JezzWTF/VibeVoice.git
- No machine-local paths; works identically on any clone
This commit is contained in:
LyAhn
2026-04-30 21:30:07 +01:00
parent 7591d15a52
commit 98e2bf9237
4 changed files with 36 additions and 496 deletions
Download Patch File Download Diff File Expand all files Collapse all files
server/uv.lock
Generated
+8 -8
View File
@@ -1479,7 +1479,7 @@ name = "nvidia-cudnn-cu12"
version = "9.1.0.70"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "nvidia-cublas-cu12" },
{ name = "nvidia-cublas-cu12", marker = "(python_full_version < '3.11' and sys_platform == 'emscripten') or (python_full_version < '3.11' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
]
wheels = [
{ url = "https://files.pythonhosted.org/packages/9f/fd/713452cd72343f682b1c7b9321e23829f00b842ceaedcda96e742ea0b0b3/nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl", hash = "sha256:165764f44ef8c61fcdfdfdbe769d687e06374059fbb388b6c89ecb0e28793a6f", size = 664752741 },
@@ -1490,7 +1490,7 @@ name = "nvidia-cufft-cu12"
version = "11.2.1.3"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "nvidia-nvjitlink-cu12" },
{ name = "nvidia-nvjitlink-cu12", marker = "(python_full_version < '3.11' and sys_platform == 'emscripten') or (python_full_version < '3.11' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
]
wheels = [
{ url = "https://files.pythonhosted.org/packages/27/94/3266821f65b92b3138631e9c8e7fe1fb513804ac934485a8d05776e1dd43/nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl", hash = "sha256:f083fc24912aa410be21fa16d157fed2055dab1cc4b6934a0e03cba69eb242b9", size = 211459117 },
@@ -1509,9 +1509,9 @@ name = "nvidia-cusolver-cu12"
version = "11.6.1.9"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "nvidia-cublas-cu12" },
{ name = "nvidia-cusparse-cu12" },
{ name = "nvidia-nvjitlink-cu12" },
{ name = "nvidia-cublas-cu12", marker = "(python_full_version < '3.11' and sys_platform == 'emscripten') or (python_full_version < '3.11' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
{ name = "nvidia-cusparse-cu12", marker = "(python_full_version < '3.11' and sys_platform == 'emscripten') or (python_full_version < '3.11' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
{ name = "nvidia-nvjitlink-cu12", marker = "(python_full_version < '3.11' and sys_platform == 'emscripten') or (python_full_version < '3.11' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
]
wheels = [
{ url = "https://files.pythonhosted.org/packages/3a/e1/5b9089a4b2a4790dfdea8b3a006052cfecff58139d5a4e34cb1a51df8d6f/nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl", hash = "sha256:19e33fa442bcfd085b3086c4ebf7e8debc07cfe01e11513cc6d332fd918ac260", size = 127936057 },
@@ -1522,7 +1522,7 @@ name = "nvidia-cusparse-cu12"
version = "12.3.1.170"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "nvidia-nvjitlink-cu12" },
{ name = "nvidia-nvjitlink-cu12", marker = "(python_full_version < '3.11' and sys_platform == 'emscripten') or (python_full_version < '3.11' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
]
wheels = [
{ url = "https://files.pythonhosted.org/packages/db/f7/97a9ea26ed4bbbfc2d470994b8b4f338ef663be97b8f677519ac195e113d/nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl", hash = "sha256:ea4f11a2904e2a8dc4b1833cc1b5181cde564edd0d5cd33e3c168eff2d1863f1", size = 207454763 },
@@ -3109,13 +3109,13 @@ requires-dist = [
{ name = "torch", specifier = ">=2.0.0", index = "https://download.pytorch.org/whl/cu124" },
{ name = "transformers", specifier = "==4.51.3" },
{ name = "uvicorn", extras = ["standard"], specifier = ">=0.29.0" },
{ name = "vibevoice", git = "https://github.com/microsoft/VibeVoice.git" },
{ name = "vibevoice", git = "https://github.com/JezzWTF/VibeVoice.git" },
]
[[package]]
name = "vibevoice"
version = "1.0.0"
source = { git = "https://github.com/microsoft/VibeVoice.git#e73d1e17c3754f046352014856a922f8208fb5d3" }
source = { git = "https://github.com/JezzWTF/VibeVoice.git#e76701f17a0d93cd612d56f0db5865a615c4d16e" }
dependencies = [
{ name = "absl-py" },
{ name = "accelerate" },