`compile_and_save` needs twice the engine size on disk while it saves to ExecuTorch

Abierto
  • ¿Algo no está bien?
#5,041 0 comentarios 0 reacciones 0 asignados Ver en GitHub

Los mantenedores suelen responder en 3 días

Nadie ha tomado este issue todavía.

Evaluación

Dificultad
4/5
Tiempo estimado
3-5 días
Aptitud para principiantes
18/100
Tipo de issue
Error
Claridad
Bastante claro
Estado de actividad
Activo
Stack tecnológico
python, pytorch
Área
data, devtools

Línea de trabajo

The save path is in compile_and_save in the Torch-TensorRT Python package, which writes each built engine to a temporary file before the ExecuTorch copy; the repro script in the issue measures peak disk use and is the check for done. The fix spans two projects: the ExecuTorch file-writing code that would need to punch holes in owned file-backed data after each chunk is copied, and the Torch-TensorRT hand-off of offloaded engine files. Start by reading how engine files are written and passed to ExecuTorch, then confirm the disk peak drops to about one copy.

Escrito por el modelo de indexación a partir del texto del issue.

Descripción

What is wrong

compile_and_save writes each engine to a temporary file as soon as it is built. With output_format="executorch", the save then copies each file into the .pte (or .ptd). The temporary files are deleted only when the call returns. So at the end of the save, every engine is on disk twice.

For a large single-engine program this decides whether the export fits. #5026 lets the caller move the files to another disk, which helps, but the space is still needed.

What this blocks

No policy in pytorch/executorch#24353 is listed as failing because of this. It costs disk.
Any export with output_format="executorch" needs free space for twice its engines, so a large single-engine program needs twice its size free. That can decide whether it fits on a Jetson or a DGX Spark.
A fix lets an export fit when the free disk is only a little larger than the program.

Repro
import os, shutil, tempfile, threading, time
import torch, torch_tensorrt

work = tempfile.mkdtemp()
os.environ["TMPDIR"] = tempfile.tempdir = os.path.join(work, "tmp")
os.makedirs(tempfile.tempdir)
out = os.path.join(work, "model.pte")

def used(path):
    return sum(os.stat(os.path.join(r, f)).st_blocks * 512 for r, _, fs in os.walk(path) for f in fs)

peak, stop = [0], threading.Event()
def watch():
    while not stop.is_set():
        peak[0] = max(peak[0], used(work))
        time.sleep(0.2)

model = torch.nn.Sequential(*[torch.nn.Linear(8192, 8192, bias=False) for _ in range(32)]).cuda().bfloat16().eval()
x = torch.randn(4, 8192, device="cuda", dtype=torch.bfloat16)
ep = torch.export.export(model, (x,))
threading.Thread(target=watch, daemon=True).start()
torch_tensorrt.compile_and_save(ep, out, output_format="executorch", arg_inputs=[x], min_block_size=1)
stop.set()
print(f"program {os.path.getsize(out) / 2**30:.2f} GiB, disk peak {peak[0] / 2**30:.2f} GiB")
shutil.rmtree(work)
Actual
program 4.00 GiB, disk peak 8.00 GiB
Expected

The peak is about one copy. A proposal in 2 small parts:

  1. ExecuTorch: file-backed data that the caller marks as owned is consumed by the write. After each chunk is copied, that range of the source is released (fallocate with FALLOC_FL_PUNCH_HOLE, supported on ext4, XFS and btrfs), and the file is removed at the end. Elsewhere it copies as today.
  2. Torch-TensorRT: hand each offloaded engine file to ExecuTorch as owned data, since nothing reads it after the save.
Versions

torch 2.15.0 (CUDA 13.2), torch_tensorrt 2.15.0, executorch 1.6.0, TensorRT 11.4.0.106. Script run on H100, driver 580.126.09 (btrfs).

Related: #4863 (keeping built engines on disk until the save, which is where the temporary files come from), #5026.

Lenguaje dominante
Python
Estrellas
3k
Forks
421
Merge medio
4 d 7 h
PR fusionados (30 d)
62

Preparar el entorno

Primeros pasos

  1. Lee el issue completo y luego la guía de contribución del proyecto.
  2. Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
  3. Haz un fork del repositorio y trabaja en una rama.
  4. Abre un pull request que haga referencia al número del issue.

Más de pytorch/TensorRT

Todos los issues de pytorch/TensorRT

Issues similares

Más issues de Python

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.