feat: add GPU inference option to web UI#34
Open
EruditionHerta wants to merge 1 commit into
Open
Conversation
Allow users to select CUDA device for inference in the web interface. Previously the app was forced to CPU-only mode. Now supports: - `--device cuda` to start on GPU - `--device auto` to auto-detect (GPU if available, else CPU) - Device selector dropdown in the web UI - Dynamic GPU runtime creation when requested per-request - `/health` endpoint reports `cuda_available`
Closed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Allow users to select CUDA device for inference in the web interface
Previously the app forced CPU-only mode regardless of
--deviceflagNow supports
--device cuda,--device auto, and per-request device selection via the web UI dropdownChanges
main(): Removed forced CPU override, addedcuda/autodevice resolution with CUDA availability detectionRequestRuntimeManager: Extendednormalize_requested_execution_device()whitelist to acceptcudaandcuda:N, added_build_cuda_runtime_locked()for dynamic GPU runtime creationWeb UI: Added Device selector dropdown (Default/CPU/CUDA:N) in Generation Options
API endpoints:
/api/generateand/api/generate-stream/startacceptexecution_deviceparameter,/healthreportscuda_availableTest Plan
python app.py --device cpu(default behavior unchanged)python app.py --device cuda(GPU mode)python app.py --device auto(auto-detect)