Repository navigation
voxtype-bin: list cudnn as an optional dependency for ONNX CUDA - #977
Open
EmanuelMedinaAraujo wants to merge 1 commit into
Open
EmanuelMedinaAraujo wants to merge 1 commit into
EmanuelMedinaAraujo wants to merge 1 commit into
Conversation
The CUDA ONNX provider libraries shipped in /usr/lib/voxtype/cuda-13 and cuda-12 both have a NEEDED entry for libcudnn.so.9, but no optdepend provides it. Add cudnn next to the CUDA entries so users who pick the ONNX CUDA engine can find the missing library. pkgrel is left alone on purpose: the built package is unchanged, so the entry can ship with the next voxtype release. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
voxtype-binlistscudaas an optional dependency for its ONNX CUDA engines, but notcudnn, which those engines also need. With onlycudainstalled the CUDA provider fails to load and Voxtype falls back to the CPU.This adds one
optdepends_x86_64line:Evidence
readelf -don the shippedlibonnxruntime_providers_cuda.soshowsNEEDED libcudnn.so.9in both/usr/lib/voxtype/cuda-13/and/usr/lib/voxtype/cuda-12/.lddon the cuda-13 provider reportedlibcudnn.so.9 => not foundon my machine.cuda 13.3.1-1andcudnn 9.25.1.1-1installed, the cuda-13 build loads and transcribes on the GPU (RTX 3050 Mobile, driver 610.57.04,voxtype-bin 1.1.0-2): Parakeet v2 and Cohere q4 both run through the CUDA execution provider and exit cleanly.cudnndepends oncuda>=13, so the entry is worded for the CUDA 13 engine only.omaspeak-binandomawake-binin this repo already listcudnnas an optdepend.pkgrel
Not bumped, on purpose. The built package is byte-for-byte the same, and
voxtype-binis on the fast ring, so a bump would make every user re-download about 345 MB for one metadata line. I expect the build check's "Change will not ship" warning; the entry would ship with the next voxtype release. Happy to add the bump if you would rather ship it now.The package was not rebuilt locally; the change is metadata only.
🤖 Generated with Claude Code