makepad/libs/ai/metal/src/backend_kind.rs
Admin 7f59912916 libs/ai: one AI stack, replacing libs/ggml, llama, mlx, cuda, tts, voice2 and pbr_paint
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.
2026-08-23 01:34:35 +02:00

27 lines
668 B
Rust

#[derive(Clone, Copy, Debug, Eq, PartialEq, Hash)]
pub enum BackendKind {
Metal,
Vulkan,
Cuda,
}
#[derive(Clone, Debug, Default, Eq, PartialEq)]
pub struct BackendCapabilities {
pub bf16: bool,
pub tensor_cores: bool,
pub max_buffer_size: Option<usize>,
pub max_threadgroup_memory: Option<usize>,
pub subgroup_width: Option<usize>,
pub asynchronous: bool,
pub host_buffer: bool,
pub buffer_from_host_ptr: bool,
pub events: bool,
}
#[derive(Clone, Debug, Eq, PartialEq)]
pub struct BackendInfo {
pub kind: BackendKind,
pub name: String,
pub description: String,
pub capabilities: BackendCapabilities,
}