Squash of 54 work commits (Sep 1–12):6251f7cai-hub: body domain — live pose packets ride the realtime sessionea50c77chat_ui: the feed's session gets its profile brief backf51b5f3ai-body: the crate for the native SAM 3D Body port, with its weights reader8211ae6ai-body: the MHR rig and the pose head's parameter decoding, oracle-exact9e343a8ai-body: the DINOv3 ViT-H+/16 backbone, crop and ray conditioning; Metal gains rope-half and affine layer norm69d842cai-body: the promptable pose decoder and its refinement loop, oracle-matched on Metal66e5e2fai-hub: SAM 3D Body runs natively — `sam3dbody` on the body domain, oracle-matched end to enda634198ai-hub: the body-native commit carried a peer's in-flight hub hunks; put them back where they were9ff44e8ai-hub: the body-native wiring, this time only the lane's hunks6a1c16bai-body: third-party notices — what the port is implemented after, and what it is notd78411aai-body: the per-step work moves to the GPUb22259bai-body: the context stays on the GPU; only the pose token leaves the loop346f31fai-body: flash attention for the head-dim-64 blocks45b5b98ai-body: the crop size is a runtime knob, and the loop reports where its time goes4be6d19ai-body: the test modules import the grid constants they still use7598346ai-body: tensor-core GEMMs for the backbone, and the rig's correctives only where they counta9ce596ai-body: the crop warp runs across cores8964ba6ai-body: an FP8 backbone mode, off by default, measured against the oraclea2aaa8fai-body: the FP8 bias rides a column-broadcast add on the deviced53c77dmetal: a device-resident ViT stack, and the body backbone rides itd006d0ametal: resident f32 linears keep their weight on the device525ba1cmetal: a device-resident two-way decoder layer, and the body decoder rides itc9e6d88ai-body: the hands pass — hand crops, the hand decoder, the hand-mode rig and the wrist fusion62dff26ai-body: the mask prompt — a person's segmentation mask conditions the body passa648cf8ai-hub: body session options — hands, detect, persons=N8c568dfai-hub: drop the SAM 3D Body reference worker backend7ff875aai-hub: keep a peer's in-flight beats/notes/local work out of the body commits31e5faaai-hub: local model runner, licence acknowledgements, a shared install panel; Beat This!, Basic Pitch and the Salamander drum-kit entriesb94bc58ai-services: the wire, the app port and the panel state — one conversation, many apps2acb798ai-services: wire v2 — endpoints, receiver-side caps, result disposition8ae0ffbai-services: the engine core — registry, router and conversation, tested against a scripted model2308736ai-services: the real models behind the engine feature — local through the hub, Claude, and nonec3f631dlivepipe: one reusable pipe from a camera to a fleet node and backff62db3ai libs: the runtime env-var cleanup — precision is a per-caller policy, not an environment side channel04a94efrealtime: one service-log line when a live session opens and one when it closes0ecb81cai models: the model-crates env-var cleanup — 172 research knobs gone, the unset default is the code4ca36c1ai hub + services: the assistant's model comes from wherever it is resident — the fleet chat box, with tools, then the local weights432121eaichat engine + wm: launch, then use — the assistant continues in the same turn once the app it started is on the bus7a5bf69ai-hub registry: the Salamander drumkit samples come from the makepad.nl mirror — the GitHub repo only carries the .sfz files102ffc5ai-services: messages on the bus — a manifest declares topics, the engine subscribes on a tool's behalf or by ToolResult.subscribe, a service publishes Message frames, an idle conversation wakes on a message as an event turn under rate laws; the WM bus forwards the new frames; every app that matches the wire gets its arma837792hub + flow: a whitespace-only chat completion is retried once and then fails instead of passing as an answer; a flow's model is a fleet model id unless it names a weight file on disk; chat models show under the text domain in /v1/modelsbc6c620hub + flow: what the chat review found — the in-process route retries an empty completion too, a node says whether its prefill opened thinking so a brief-mode answer is never discarded, a preferred model falls back to normal election when no node has it, discovery keeps looking for the preferred model until patience runs out75c3441hub: the PRO 6000 serves image as well as chat and textad5e98bhub registry: flux2-dev's VRAM estimate is its measured peak, 30 GBc7241e0hub: a node that evicted every resident releases its cached allocator pool before refusing a load or publishing usable VRAM30575f0flow: route generation by request workload1be1e21ai-hub: gate downloads by disk capacity and recover fleet admission df6b394 filesystem_watcher, bounded_http, ai services: live and tool prerequisites 79ebdb9 ai-hub: add a native Pixal3D image-to-3D backend 0ba0d74 ai-hub: propagate typed refusals under reject queue policy cc6c872 Speed up H3 conditioning and video decoding e512059 Fix Qwen vision residency and generated material colors 2864f68 ai-hub http client: bound every plain TCP connect to 3 s per address 3d93229 ai: CUDA is a Linux/Windows-only dependency; the hub library defaults to llm + stt Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
98 lines
3.9 KiB
Rust
98 lines
3.9 KiB
Rust
//! Native GPU smoke test / profiler. Run the release binary directly:
|
|
//! pixal_generate <verified-weights-dir> <input.png> <output.glb> [1024|1536] [REPEATS]
|
|
//! Weights use the filenames below; downloads and hashes still use the registry.
|
|
#[cfg(feature = "mesh")]
|
|
fn main() -> Result<(), Box<dyn std::error::Error>> {
|
|
use makepad_ai_hub::backend::{BackendCtx, CancelToken, ContentBackend, GenerateParams};
|
|
use makepad_ai_hub::download::Downloader;
|
|
use makepad_ai_hub::protocol::{GenerateRequestJson, PixalOptionsJson};
|
|
use makepad_ai_hub::registry::Registry;
|
|
let args: Vec<_> = std::env::args().collect();
|
|
if args.len() < 4 {
|
|
return Err(
|
|
"usage: pixal_generate WEIGHTS INPUT.png OUTPUT.glb [1024|1536] [REPEATS]".into(),
|
|
);
|
|
}
|
|
let root = std::path::Path::new(&args[1]);
|
|
let registry = Registry::embedded()?;
|
|
let mut spec = registry
|
|
.find("pixal3d")
|
|
.ok_or("Pixal3D registry entry missing")?
|
|
.clone();
|
|
for file in &mut spec.files {
|
|
let name = match file.role.as_deref().unwrap_or("") {
|
|
"ss-flow" | "shape-flow-512" | "shape-flow-1024" | "texture-flow-1024" => {
|
|
"pixal3d_bf16.safetensors".to_string()
|
|
}
|
|
"dino-conditioner" => "dino_naf.safetensors".to_string(),
|
|
role => format!("{role}.safetensors"),
|
|
};
|
|
file.cache_as = name;
|
|
}
|
|
let downloader = Downloader::new("https://huggingface.co", None)?;
|
|
let cancel = CancelToken::new();
|
|
let mut download =
|
|
|p: makepad_ai_hub::download::DownloadProgress| eprintln!("download {} {}", p.file, p.done);
|
|
let mut load = |stage: &str, progress: f64| eprintln!("load {progress:.3} {stage}");
|
|
let mut context = BackendCtx {
|
|
spec: &spec,
|
|
cache_dir: root,
|
|
downloader: &downloader,
|
|
download_progress: &mut download,
|
|
cancel: &cancel,
|
|
progress: &mut load,
|
|
};
|
|
let mut backend = makepad_ai_hub::trellis_backend::TrellisBackend::new_trellis("pixal3d");
|
|
backend.ensure_loaded(&mut context)?;
|
|
let mut params = GenerateParams::from_request(&GenerateRequestJson {
|
|
model: "pixal3d".into(),
|
|
seed: Some(42),
|
|
texture: Some(true),
|
|
remesh_resolution: Some(256),
|
|
texture_size: Some(1024),
|
|
decimation_target: Some(80_000),
|
|
pixal: Some(PixalOptionsJson {
|
|
resolution: Some(args.get(4).map(|s| s.parse()).transpose()?.unwrap_or(1024)),
|
|
camera_fov: Some(49.13),
|
|
structure_seed: Some(56),
|
|
texture_seed: Some(43),
|
|
shape_steps: Some(20),
|
|
}),
|
|
..Default::default()
|
|
})?;
|
|
params.input_bytes = std::fs::read(&args[2])?;
|
|
let repeats: usize = args.get(5).map(|s| s.parse()).transpose()?.unwrap_or(1);
|
|
if !(1..=100).contains(&repeats) {
|
|
return Err("REPEATS must be 1..100".into());
|
|
}
|
|
let result = (|| -> Result<(), Box<dyn std::error::Error>> {
|
|
for trial in 0..repeats {
|
|
let started = std::time::Instant::now();
|
|
let mut progress = |stage: &str, value: f64| {
|
|
eprintln!("{:.3}s {value:.3} {stage}", started.elapsed().as_secs_f64())
|
|
};
|
|
let artifacts = backend.generate(¶ms, &mut progress, &cancel)?;
|
|
let elapsed = started.elapsed().as_secs_f64();
|
|
let artifact = artifacts.first().ok_or("no Pixal3D output")?;
|
|
let path = if repeats == 1 {
|
|
args[3].clone()
|
|
} else {
|
|
format!("{}.{trial}.glb", args[3])
|
|
};
|
|
std::fs::write(path, &artifact.bytes)?;
|
|
eprintln!(
|
|
"native Pixal3D trial {trial}: {elapsed:.3}s, {} GLB bytes",
|
|
artifact.bytes.len()
|
|
);
|
|
}
|
|
Ok(())
|
|
})();
|
|
backend.unload()?;
|
|
result
|
|
}
|
|
|
|
#[cfg(not(feature = "mesh"))]
|
|
fn main() {
|
|
eprintln!("build with --features mesh");
|
|
std::process::exit(1);
|
|
}
|