Labyricorn/voicebox
1
0
Fork 0
mirror of https://github.com/jamiepine/voicebox.git synced 2026-09-18 14:20:42 -07:00
Code Issues Packages Projects Releases Wiki Activity

feat: split CUDA backend into independently versioned server + libs archives

Browse Source 
Switch CUDA builds from PyInstaller --onefile to --onedir and split the
output into two separately versioned archives:

1. Server core (~200-400MB) — versioned with the app, redownloaded on
   every app update
2. CUDA libs (~2GB) — versioned independently (cu126-v1), only
   redownloaded when the CUDA toolkit or torch version changes

This eliminates the ~2.4GB full redownload on every version bump.
After initial setup, most app updates only need ~200-400MB.

Closes #297
This commit is contained in:
James Pine
2026-03-17 04:04:17 -07:00
parent 2c1ee94891
commit 564d787927
6 changed files with 511 additions and 142 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tauri/src-tauri/src/main.rs
+16 -10
View File
@@ -197,22 +197,24 @@ async fn start_server(
println!("Data directory: {:?}", data_dir);
println!("Remote mode: {}", remote.unwrap_or(false));
// Check for CUDA backend binary in data directory
// Check for CUDA backend in data directory (onedir layout: backends/cuda/)
let cuda_binary = {
let backends_dir = data_dir.join("backends");
let cuda_dir = data_dir.join("backends").join("cuda");
let cuda_name = if cfg!(windows) {
"voicebox-server-cuda.exe"
} else {
"voicebox-server-cuda"
};
let path = backends_dir.join(cuda_name);
if path.exists() {
println!("Found CUDA backend binary at {:?}", path);
let exe_path = cuda_dir.join(cuda_name);
if exe_path.exists() {
println!("Found CUDA backend at {:?}", cuda_dir);
// Version check: run --version and compare to app version
// Version check: run --version from the onedir directory so
// PyInstaller can find its support files for the fast --version path
let app_version = app.config().version.clone().unwrap_or_default();
let version_ok = match std::process::Command::new(&path)
let version_ok = match std::process::Command::new(&exe_path)
.arg("--version")
.current_dir(&cuda_dir)
.output()
{
Ok(output) => {
@@ -237,7 +239,7 @@ async fn start_server(
};
if version_ok {
Some(path)
Some(exe_path)
} else {
None
}
@@ -300,10 +302,14 @@ async fn start_server(
println!("Custom models directory: {}", dir);
}
// If CUDA binary exists, launch it directly instead of the bundled sidecar
// If CUDA binary exists, launch it from the onedir directory.
// .current_dir() is critical: PyInstaller onedir expects all DLLs and
// support files (nvidia/, _internal/, etc.) relative to the exe.
let spawn_result = if let Some(ref cuda_path) = cuda_binary {
println!("Launching CUDA backend: {:?}", cuda_path);
let cuda_dir = cuda_path.parent().unwrap();
println!("Launching CUDA backend: {:?} (cwd: {:?})", cuda_path, cuda_dir);
let mut cmd = app.shell().command(cuda_path.to_str().unwrap());
cmd = cmd.current_dir(cuda_dir);
cmd = cmd.args(["--data-dir", &data_dir_str, "--port", &port_str, "--parent-pid", &parent_pid_str]);
if is_remote {
cmd = cmd.args(["--host", "0.0.0.0"]);