upstream-archive/VoiceStudio
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: install cuDNN 8 compat libraries in the CUDA Docker image

Browse Source 
The CUDA base image is pytorch/pytorch:2.8.0-cuda12.8-cudnn9-runtime, so it
ships cuDNN 9. CTranslate2 — WhisperX and faster-whisper — links cuDNN 8, and
its absence aborts the backend process outright rather than raising (#1371).

scripts/setup.py side-loads the cuDNN 8 libraries for source installs, but the
Dockerfile never did, so every CTranslate2 ASR engine was unavailable in Docker
and the demo synthesis timed out with libcudnn_ops_infer.so.8 missing.

Install the same nvidia-cudnn-cu12==8.9.7.29 shim during the image build,
deriving the target from sys.prefix so it matches where backend/core/cudnn8.py
searches rather than hardcoding the conda path — sys.prefix differs between the
conda-based CUDA image and the ROCm venv. Guarded to GPU_FLAVOR=cuda, since
ROCm does not use cuDNN, and --no-deps keeps the base image's torch stack
untouched. A post-install assert fails the build if no .so.8 libraries landed,
rather than letting it resurface as the same runtime warning.

Fixes #2050
This commit is contained in:
basil-k-aji-dev
2026-09-13 23:51:57 +05:30
parent eaf8bb9538
commit a628ba161e
1 changed files with 21 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
deploy/Dockerfile
+21
View File
@@ -103,6 +103,27 @@ RUN python3 -c "import os, torch, torchaudio, torchvision; \
import torchvision.ops; torchvision.ops.nms; \ import torchvision.ops; torchvision.ops.nms; \
print('torchvision C++ ops resolve against this torch')" print('torchvision C++ ops resolve against this torch')"
# CTranslate2 (WhisperX, faster-whisper) links cuDNN 8, but the CUDA base image
# ships cuDNN 9, so libcudnn_ops_infer.so.8 is absent and loading it aborts the
# backend process outright rather than raising (#1371). scripts/setup.py
# side-loads the cuDNN 8 libraries for source installs; the image needs the same
# shim or Docker users lose every CTranslate2 ASR engine (#2050).
#
# The target is derived from sys.prefix rather than hardcoded: backend/core/
# cudnn8.py looks for <sys.prefix>/lib/pythonX.Y/site-packages/cudnn8_compat,
# and sys.prefix differs between the conda-based CUDA image and the ROCm venv.
# --no-deps keeps this to the cuDNN wheels alone, leaving the base image's torch
# stack untouched. Skipped for ROCm, which does not use cuDNN.
RUN if [ "$GPU_FLAVOR" = "cuda" ]; then \
target="$(python3 -c "import os, sys; print(os.path.join(sys.prefix, 'lib', 'python%d.%d' % sys.version_info[:2], 'site-packages', 'cudnn8_compat'))")" && \
uv pip install --python "$(command -v python3)" --no-cache --no-deps \
--target "$target" nvidia-cudnn-cu12==8.9.7.29 && \
python3 -c "import os, sys; d = os.path.join(sys.prefix, 'lib', 'python%d.%d' % sys.version_info[:2], 'site-packages', 'cudnn8_compat', 'nvidia', 'cudnn', 'lib'); \
libs = [f for f in os.listdir(d) if '.so.8' in f]; \
assert libs, 'cudnn8_compat installed but no .so.8 libraries in ' + d; \
print('cuDNN 8 compat libraries: %d' % len(libs))"; \
fi
# Copy application source # Copy application source
COPY backend/ ./backend/ COPY backend/ ./backend/
COPY omnivoice/ ./omnivoice/ COPY omnivoice/ ./omnivoice/