7f59912916
The model code was spread across eight crates that had grown into each other:
ggml and cuda and mlx each owned part of a tensor runtime, llama and tts and
voice2 each owned part of a model, and libs/diffusion owned everything else.
They are now one tree with an explicit shape:
libs/ai/cuda — kernels and launch surface
libs/ai/metal — Metal shaders and the shim
libs/ai/llm — the language-model runtime (sessions, lanes, contexts,
the CUDA and Metal executors, the compiled Metal path)
libs/ai/models/ — common, flux, h3, music, paint, speech, stems, vision
libs/diffusion is not deleted but demoted: what remains is the VALIDATOR
crate — several dozen `*_validate.rs` oracles that check a native
implementation against a reference, which is where they belong now that the
implementations live next door.
The functional work inside the move is mostly in the LLM runtime: N lanes that
draft while one verify batch serves all of them, per-slot prefill over a shared
folded attention arena, speculation that survives batching, and a scheduler
that reports rather than publishes. And in the CUDA build: a machine without
usable CUDA must still LINK (and say so), the default kernel arch is the
building machine's GPU, `NO_CUDA` forces the stub even where the toolkit
exists, and kernels compile in parallel with progress.
libs/video_flow is new here: classical optical flow estimation and the `mkfl`
motion-field payload — a flow field measured from a clip without a model,
which is what drives free-rate bounce-looping playback and the uprez/tween
enhance pipe.
34 lines
652 B
TOML
34 lines
652 B
TOML
[package]
|
|
name = "makepad-ai-speech"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
description = "Speech family: IndexTTS-2.5 + Kokoro (aiarch.md §1)."
|
|
license = "MIT"
|
|
|
|
[dependencies]
|
|
makepad-ai-common = { path = "../common" }
|
|
makepad-ai-loader = { path = "../../loader" }
|
|
makepad-ai-sfx = { path = "../sfx" }
|
|
|
|
[dev-dependencies]
|
|
makepad-voice = { path = "../../../voice" }
|
|
|
|
[[bin]]
|
|
name = "g2p_test"
|
|
path = "src/bin/g2p_test.rs"
|
|
|
|
[[bin]]
|
|
name = "har_bisect"
|
|
path = "src/bin/har_bisect.rs"
|
|
|
|
[[bin]]
|
|
name = "kokoro_probe"
|
|
path = "src/bin/kokoro_probe.rs"
|
|
|
|
[[bin]]
|
|
name = "parity"
|
|
path = "src/bin/parity.rs"
|
|
|
|
[[bin]]
|
|
name = "tts_test"
|
|
path = "src/bin/tts_test.rs"
|