New nn layers: - ConvTranspose1d with stride, padding, output_padding (9 tests) - LSTM/BiLSTM with multi-layer support and hidden state (10 tests) Audio source separation: - Demucs ONNX inference with segmented overlap-add processing - Native HtDemucs architecture (encoder/decoder with BiLSTM bottleneck) - StemType enum: vocals, drums, bass, other, piano, guitar Audio generation: - Stable Audio Open ONNX inference scaffold - GenerationParams (prompt, duration, steps, cfg_scale, seed) ONNX export scripts: - export_demucs_onnx.py — Demucs v4 to ONNX with segment chunking - export_stable_audio_onnx.py — Stable Audio Open components - export_mert_onnx.py — MERT music understanding transformer Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
44 lines
1.0 KiB
TOML
44 lines
1.0 KiB
TOML
[package]
|
|
name = "rtx-multimodal"
|
|
version = "1.0.0"
|
|
edition.workspace = true
|
|
rust-version = "1.92"
|
|
authors.workspace = true
|
|
license.workspace = true
|
|
repository.workspace = true
|
|
|
|
[dependencies]
|
|
rtx-tensor = { path = "../../core/rtx-tensor" }
|
|
rtx-runtime = { path = "../../core/rtx-runtime" }
|
|
rtx-polygraph = { path = "../../specialized/rtx-polygraph" }
|
|
rtx-transformers = { path = "../../training/rtx-transformers" }
|
|
rtx-flash-attention = { path = "../../training/rtx-flash-attention" }
|
|
rtx-nn = { path = "../../core/rtx-nn" }
|
|
rtx-onnx = { path = "../../production/rtx-onnx", optional = true }
|
|
image = "0.24"
|
|
hound = "3.5"
|
|
anyhow.workspace = true
|
|
thiserror.workspace = true
|
|
serde.workspace = true
|
|
serde_json.workspace = true
|
|
tracing.workspace = true
|
|
tokio.workspace = true
|
|
futures.workspace = true
|
|
rand.workspace = true
|
|
approx = "0.5"
|
|
|
|
[features]
|
|
default = []
|
|
demucs = ["rtx-onnx"]
|
|
generation = ["rtx-onnx"]
|
|
|
|
[dev-dependencies]
|
|
criterion = { version = "0.5", features = ["html_reports"] }
|
|
|
|
[[bench]]
|
|
name = "multimodal_bench"
|
|
harness = false
|
|
|
|
[lints]
|
|
workspace = true
|