makepad/libs/ai/metal/build.rs
Admin 60615db4ed libs: ai hub/models/cuda, speech, chat_ui
Squash of 54 work commits (Sep 1–12):
  6251f7c  ai-hub: body domain — live pose packets ride the realtime session
  ea50c77  chat_ui: the feed's session gets its profile brief back
  f51b5f3  ai-body: the crate for the native SAM 3D Body port, with its weights reader
  8211ae6  ai-body: the MHR rig and the pose head's parameter decoding, oracle-exact
  9e343a8  ai-body: the DINOv3 ViT-H+/16 backbone, crop and ray conditioning; Metal gains rope-half and affine layer norm
  69d842c  ai-body: the promptable pose decoder and its refinement loop, oracle-matched on Metal
  66e5e2f  ai-hub: SAM 3D Body runs natively — `sam3dbody` on the body domain, oracle-matched end to end
  a634198  ai-hub: the body-native commit carried a peer's in-flight hub hunks; put them back where they were
  9ff44e8  ai-hub: the body-native wiring, this time only the lane's hunks
  6a1c16b  ai-body: third-party notices — what the port is implemented after, and what it is not
  d78411a  ai-body: the per-step work moves to the GPU
  b22259b  ai-body: the context stays on the GPU; only the pose token leaves the loop
  346f31f  ai-body: flash attention for the head-dim-64 blocks
  45b5b98  ai-body: the crop size is a runtime knob, and the loop reports where its time goes
  4be6d19  ai-body: the test modules import the grid constants they still use
  7598346  ai-body: tensor-core GEMMs for the backbone, and the rig's correctives only where they count
  a9ce596  ai-body: the crop warp runs across cores
  8964ba6  ai-body: an FP8 backbone mode, off by default, measured against the oracle
  a2aaa8f  ai-body: the FP8 bias rides a column-broadcast add on the device
  d53c77d  metal: a device-resident ViT stack, and the body backbone rides it
  d006d0a  metal: resident f32 linears keep their weight on the device
  525ba1c  metal: a device-resident two-way decoder layer, and the body decoder rides it
  c9e6d88  ai-body: the hands pass — hand crops, the hand decoder, the hand-mode rig and the wrist fusion
  62dff26  ai-body: the mask prompt — a person's segmentation mask conditions the body pass
  a648cf8  ai-hub: body session options — hands, detect, persons=N
  8c568df  ai-hub: drop the SAM 3D Body reference worker backend
  7ff875a  ai-hub: keep a peer's in-flight beats/notes/local work out of the body commits
  31e5faa  ai-hub: local model runner, licence acknowledgements, a shared install panel; Beat This!, Basic Pitch and the Salamander drum-kit entries
  b94bc58  ai-services: the wire, the app port and the panel state — one conversation, many apps
  2acb798  ai-services: wire v2 — endpoints, receiver-side caps, result disposition
  8ae0ffb  ai-services: the engine core — registry, router and conversation, tested against a scripted model
  2308736  ai-services: the real models behind the engine feature — local through the hub, Claude, and none
  c3f631d  livepipe: one reusable pipe from a camera to a fleet node and back
  ff62db3  ai libs: the runtime env-var cleanup — precision is a per-caller policy, not an environment side channel
  04a94ef  realtime: one service-log line when a live session opens and one when it closes
  0ecb81c  ai models: the model-crates env-var cleanup — 172 research knobs gone, the unset default is the code
  4ca36c1  ai hub + services: the assistant's model comes from wherever it is resident — the fleet chat box, with tools, then the local weights
  432121e  aichat engine + wm: launch, then use — the assistant continues in the same turn once the app it started is on the bus
  7a5bf69  ai-hub registry: the Salamander drumkit samples come from the makepad.nl mirror — the GitHub repo only carries the .sfz files
  102ffc5  ai-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 arm
  a837792  hub + 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/models
  bc6c620  hub + 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 out
  75c3441  hub: the PRO 6000 serves image as well as chat and text
  ad5e98b  hub registry: flux2-dev's VRAM estimate is its measured peak, 30 GB
  c7241e0  hub: a node that evicted every resident releases its cached allocator pool before refusing a load or publishing usable VRAM
  30575f0  flow: route generation by request workload
  1be1e21  ai-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>
2026-09-15 13:40:31 +02:00

166 lines
7.3 KiB
Rust

use std::env;
use std::fs;
use std::process::Command;
// The metallib build for THE Metal shader store (aiarch.md §1 + §8b ring 1,
// lane T5). Absorbed verbatim from libs/ggml/build.rs::build_metallib —
// same env var names (MAKEPAD_GGML_METAL_PRECOMPILE, still read directly
// off the process environment; build scripts see it regardless of which
// crate's Cargo.toml declares it), same feature name (`metal-precompile`,
// forwarded here from makepad-ggml via
// `metal-precompile = ["makepad-ai-metal/metal-precompile"]` in
// libs/ggml/Cargo.toml so CARGO_FEATURE_METAL_PRECOMPILE lands on THIS
// build script), same three-mode behavior (precompile disabled /
// precompile attempted but failed / precompile succeeded), same output
// filename (`ggml-default.metallib`).
//
// This crate sets `links = "makepad_ai_metal"` in its Cargo.toml, so on
// success (in EVERY mode — the metallib file always exists, empty or not)
// it emits the links-metadata line `cargo:metallib=<path>`, which flows to
// immediate dependents (libs/ggml) as `DEP_MAKEPAD_AI_METAL_METALLIB`.
// libs/ggml/build.rs reads that env var and re-emits
// `cargo:rustc-env=MAKEPAD_GGML_METALLIB=<path>` (same env name as before
// the move), so `libs/ggml/src/backend/metal/{runtime,compat}.rs`'s
// `include_bytes!(env!("MAKEPAD_GGML_METALLIB"))` sites need zero edits.
//
// Two of the include_str! sites in those same files (ggml-metal.metal,
// ggml-common.h, ggml-metal-impl.h) used to reach the shader tree by a
// RELATIVE path (it used to sit right next to them). Now that the shader
// tree lives in this crate, we also emit `cargo:shader_dir=<dir>`, which
// flows to libs/ggml as `DEP_MAKEPAD_AI_METAL_SHADER_DIR`; libs/ggml's
// build.rs re-emits that as `cargo:rustc-env=MAKEPAD_GGML_METAL_SHADER_DIR=<dir>`
// and the include sites switch to
// `include_str!(concat!(env!("MAKEPAD_GGML_METAL_SHADER_DIR"), "/ggml-metal.metal"))`
// — file contents stay byte-identical, only how the path is found changes.
fn main() {
// Apple BLAS for the RIFE host-path GEMMs (rife.rs): cblas_sgemm off
// the Accelerate framework — hundreds of GFLOP/s with zero dispatch
// overhead, exactly what fifty small convolutions per frame pair want.
#[allow(clippy::needless_return)]
{
let target_os = std::env::var("CARGO_CFG_TARGET_OS").unwrap_or_default();
if target_os == "macos" || target_os == "ios" {
println!("cargo:rustc-link-lib=framework=Accelerate");
}
}
println!("cargo:rerun-if-env-changed=MAKEPAD_GGML_METAL_PRECOMPILE");
// shim.rs's non-macos CUDA bounce only compiles when makepad-ai-cuda
// actually built kernels (same links-metadata handshake models/common
// uses); otherwise a None-returning stub takes its place.
println!("cargo:rustc-check-cfg=cfg(makepad_ai_cuda_kernels)");
if env::var("DEP_MAKEPAD_AI_CUDA_KERNELS").as_deref() == Ok("1") {
println!("cargo:rustc-cfg=makepad_ai_cuda_kernels");
}
let target_os = env::var("CARGO_CFG_TARGET_OS").unwrap_or_default();
if target_os == "macos" {
build_metallib();
} else {
// env! sites in macos-only modules still need a value if rustc
// type-checks them. Point at this crate's shader tree.
let manifest_dir = env::var("CARGO_MANIFEST_DIR").unwrap();
let metal_dir = format!("{manifest_dir}/shaders/ggml");
println!("cargo:rustc-env=MAKEPAD_METAL_SHADER_DIR={metal_dir}");
println!("cargo:rustc-env=MAKEPAD_GGML_METAL_SHADER_DIR={metal_dir}");
println!("cargo:rustc-env=MAKEPAD_METALLIB=/dev/null");
println!("cargo:rustc-env=MAKEPAD_GGML_METALLIB=/dev/null");
}
// non-macos targets: nothing to do, no metallib, no shader_dir line —
// dependents see DEP_MAKEPAD_AI_METAL_METALLIB / _SHADER_DIR unset.
}
fn build_metallib() {
let manifest_dir = env::var("CARGO_MANIFEST_DIR").unwrap();
let metal_dir = format!("{}/shaders/ggml", manifest_dir);
let metal_src = format!("{}/ggml-metal.metal", metal_dir);
let common_h = format!("{}/ggml-common.h", metal_dir);
let impl_h = format!("{}/ggml-metal-impl.h", metal_dir);
println!("cargo:rerun-if-changed={}", metal_src);
println!("cargo:rerun-if-changed={}", common_h);
println!("cargo:rerun-if-changed={}", impl_h);
// links-metadata handshake: flows to immediate dependents (libs/ggml)
// as DEP_MAKEPAD_AI_METAL_SHADER_DIR=<metal_dir>. Emitted unconditionally
// (independent of precompile mode) because the include_str! source
// fallback in libs/ggml needs it regardless of whether a real metallib
// was baked.
println!("cargo:shader_dir={}", metal_dir);
println!("cargo:rustc-env=MAKEPAD_METAL_SHADER_DIR={metal_dir}");
println!("cargo:rustc-env=MAKEPAD_GGML_METAL_SHADER_DIR={metal_dir}");
let precompile_default = env::var_os("CARGO_FEATURE_METAL_PRECOMPILE").is_some();
let precompile_enabled = env::var("MAKEPAD_GGML_METAL_PRECOMPILE")
.ok()
.map(|v| {
let v = v.trim().to_ascii_lowercase();
!(v.is_empty() || v == "0" || v == "false" || v == "no" || v == "off")
})
.unwrap_or(precompile_default);
let out_dir = env::var("OUT_DIR").unwrap();
let _ = fs::create_dir_all(&out_dir);
let air_path = format!("{}/ggml-metal.air", out_dir);
let metallib_path = format!("{}/ggml-default.metallib", out_dir);
if !precompile_enabled {
let _ = fs::write(&metallib_path, []);
emit_metallib_env(&metallib_path);
return;
}
let metal_status = Command::new("xcrun")
.args([
"--sdk",
"macosx",
"metal",
"-O3",
"-fno-fast-math",
// The runtime source compile defines this on bfloat-capable
// devices; the precompiled library must carry the same kernels
// (the shader drops the define itself below Metal 3.1).
"-DGGML_METAL_HAS_BF16=1",
"-c",
&metal_src,
"-I",
&metal_dir,
"-o",
&air_path,
])
.status();
let ok = metal_status.as_ref().is_ok_and(|s| s.success());
if !ok {
println!(
"cargo:warning=failed to compile ggml-metal.metal to AIR; runtime source compile will be used"
);
let _ = fs::write(&metallib_path, []);
emit_metallib_env(&metallib_path);
return;
}
let mut metallib = Command::new("xcrun");
metallib.args(["--sdk", "macosx", "metallib", &air_path]);
let metallib_status = metallib.arg("-o").arg(&metallib_path).status();
let ok = metallib_status.as_ref().is_ok_and(|s| s.success());
if !ok {
println!(
"cargo:warning=failed to build ggml default metallib; runtime source compile will be used"
);
let _ = fs::write(&metallib_path, []);
}
emit_metallib_env(&metallib_path);
}
fn emit_metallib_env(metallib_path: &str) {
// Own crate's rustc-env: harmless (this crate has no Rust code that
// reads it today), kept for parity/future use.
println!("cargo:rustc-env=MAKEPAD_METALLIB={metallib_path}");
println!("cargo:rustc-env=MAKEPAD_GGML_METALLIB={metallib_path}");
// links-metadata handshake: flows to immediate dependents (libs/ggml)
// as DEP_MAKEPAD_AI_METAL_METALLIB=<metallib_path>.
println!("cargo:metallib={}", metallib_path);
}