12 Commits
Author SHA1 Message Date
RevLayDust f34bc96399 docs(readme): update license badge to reflect mixed MIT and AGPL-3.0 license 2026-10-13 21:31:15 +07:00
RevLayDust 3479b0ebce fix(cli): remove unsupported directml prefix from device validation in model_resolver 2026-10-13 21:24:55 +07:00
RevLayDust 9949774608 chore(license): relicense uvr_cli to GNU AGPL v3 with SPDX headers and test coverage
- Add official GNU Affero General Public License v3.0 to uvr_cli/LICENSE

- Add SPDX-License-Identifier: AGPL-3.0-or-later and Copyright (C) 2026 RevLayDust headers to all uvr_cli modules

- Document multi-license architecture in root README.md and uvr_cli/README.md

- Add automated regression tests in tests/test_uvr_cli.py verifying license file and module SPDX headers
2026-10-12 06:23:27 +07:00
RevLayDust cb9432a4c5 docs: update benchmarks, EP restart guide, CLI device docs, and bump version to v0.2.0-beta.1 2026-10-11 08:45:49 +07:00
RevLayDust 90050a048e feat(engine): add TensorRT-RTX execution provider backend with in-memory FP16 downcast
- Implement TensorRT-RTX backend via onnxruntime-ep-nv-tensorrt-rtx plugin in engine/tensorrt_rtx/

- Support in-memory FP16 downcast for MDX-Net ONNX models with zero disk writes

- Implement automatic fallback chain: TensorRT-RTX -> CUDA -> CPU

- Add GUI execution provider selection with dynamic hardware gating

- Add CLI provider flags and model resolver support for trt_rtx

- Add install/requirements_trt_rtx.txt and stack profile tracking

- Add test suite in tests/test_tensorrt_rtx.py and test_uvr_cli.py

- Update run_uvr.bat to execute UVR.py via native CMD
2026-10-09 16:05:22 +07:00
RevLayDust 10e48a5a55 docs: document CLI parser options, add BF16 guidance, and update model scope 2026-09-20 16:42:21 +07:00
RevLayDust add0a948df perf(cli): optimize uvr_cli startup time and report pure inference elapsed time
- Implement PEP 562 lazy loading in uvr_cli/__init__.py to reduce import time from 7.85s to 0.02s
- Defer heavy inference dependencies (torch, separate, onnxruntime, numpy) into CLI command handlers
- Reduce uvr_cli --help startup latency from ~8.98s to ~0.20s (~45x faster)
- Introduce InferenceResult tuple subclass in runner.py to isolate pure model execution timing
- Accurately measure and report pure inference elapsed time in uvr_cli run and benchmark engine
- Add unit tests for CLI startup backend isolation, PEP 562 exports, and InferenceResult structure
2026-09-17 20:32:06 +07:00
RevLayDust 279836f234 fix(benchmark): correctly record custom overlap, segment size, and batch size in CSV and JSON
- Synchronize user-specified overlap, segment_size, and batch_size attributes onto HeadlessModelData
- Prioritize active overlap_mdx value when writing benchmark CSV rows and JSON summaries
- Support shorthand precision strings (fp32, fp16, bf16) in build_headless_model_data
- Add unit test coverage verifying custom bench parameters are captured in model data and CLI parsing
2026-09-12 20:54:43 +07:00
RevLayDust 4575df561e feat(benchmark): expand metadata fields and report actual CPU model name 2026-09-10 22:39:40 +07:00
RevLayDust 37090bb073 feat(cli): add progress bar, overwrite prompt, and elapsed time display 2026-09-10 22:39:24 +07:00
RevLayDust 8e54ebbf73 checkpoint(cli): preserve MVP before core fix 2026-09-08 19:42:40 +07:00
RevLayDust 4fdc3b43fd checkpoint: add initial CLI implementation 2026-09-08 17:46:31 +07:00