Labyricorn/voicebox
1
0
Fork 0
mirror of https://github.com/jamiepine/voicebox.git synced 2026-10-03 17:15:19 -07:00
Code Issues Packages Projects Releases Wiki Activity

fix(backend): prevent unbounded memory accumulation over consecutive TTS generations (#923)

Browse Source
This commit is contained in:
devangkantharia
2026-10-04 00:01:18 +00:00
committed by capy-ai-staging[bot]
parent 63f09455ef
commit 38389db82b
8 changed files with 88 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/backends/base.py
+9 -3
View File
@@ -205,17 +205,23 @@ def check_cuda_compatibility() -> tuple[bool, str | None]:
def empty_device_cache(device: str) -> None:
"""
Free cached memory on the given device (CUDA or XPU).
Free cached memory and unreferenced tensors on the given device (CUDA, XPU, MPS, CPU).
Backends should call this after unloading models so VRAM is returned
to the OS.
Backends call this after model unloading and post-generation cleanup to return
memory to the OS and prevent process heap accumulation.
"""
import gc
import torch
gc.collect()
if device == "cuda" and torch.cuda.is_available():
torch.cuda.empty_cache()
elif device == "xpu" and hasattr(torch, "xpu"):
torch.xpu.empty_cache()
elif device == "mps" and hasattr(torch.backends, "mps") and torch.backends.mps.is_available():
if hasattr(torch.mps, "empty_cache"):
torch.mps.empty_cache()
def manual_seed(seed: int, device: str) -> None: