[benchmarks] overhaul benchmarks (#11565)

* start overhauling the benchmarking suite.

* fixes

* fixes

* checking.

* checking

* fixes.

* error handling and logging.

* add flops and params.

* add more models.

* utility to fire execution of all benchmarking scripts.

* utility to push to the hub.

* push utility improvement

* seems to be working.

* okay

* add torchprofile dep.

* remove total gpu memory

* fixes

* fix

* need a big gpu

* better

* what's happening.

* okay

* separate requirements and make it nightly.

* add db population script.

* update secret name

* update secret.

* population db update

* disable db population for now.

* change to every monday

* Update .github/workflows/benchmark.yml
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* quality improvements.

* reparate hub upload step.

* repository

* remove csv

* check

* update

* update

* threading.

* update

* update

* updaye

* update

* update

* update

* remove peft dep

* upgrade runner.

* fix

* fixes

* fix merging csvs.

* push dataset to the Space repo for analysis.

* warm up.

* add a readme

* Apply suggestions from code review
Co-authored-by: Luc Georges <McPatate@users.noreply.github.com>

* address feedback

* Apply suggestions from code review

* disable db workflow.

* update to bi weekly.

* enable population

* enable

* updaye

* update

* metadata

* fix

---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: Luc Georges <McPatate@users.noreply.github.com>

benchmarks/utils.py

-import argparse
-import csv
-import gc
-import os
-from dataclasses import dataclass
-from typing import Dict, List, Union
-
-import torch
-import torch.utils.benchmark as benchmark
-
-
-GITHUB_SHA = os.getenv("GITHUB_SHA", None)
-BENCHMARK_FIELDS = [
-    "pipeline_cls",
-    "ckpt_id",
-    "batch_size",
-    "num_inference_steps",
-    "model_cpu_offload",
-    "run_compile",
-    "time (secs)",
-    "memory (gbs)",
-    "actual_gpu_memory (gbs)",
-    "github_sha",
-]
-
-PROMPT = "ghibli style, a fantasy landscape with castles"
-BASE_PATH = os.getenv("BASE_PATH", ".")
-TOTAL_GPU_MEMORY = float(os.getenv("TOTAL_GPU_MEMORY", torch.cuda.get_device_properties(0).total_memory / (1024**3)))
-
-REPO_ID = "diffusers/benchmarks"
-FINAL_CSV_FILE = "collated_results.csv"
-
-
-@dataclass
-class BenchmarkInfo:
-    time: float
-    memory: float
-
-
-def flush():
-    """Wipes off memory."""
-    gc.collect()
-    torch.cuda.empty_cache()
-    torch.cuda.reset_max_memory_allocated()
-    torch.cuda.reset_peak_memory_stats()
-
-
-def bytes_to_giga_bytes(bytes):
-    return f"{(bytes / 1024 / 1024 / 1024):.3f}"
-
-
-def benchmark_fn(f, *args, **kwargs):
-    t0 = benchmark.Timer(
-        stmt="f(*args, **kwargs)",
-        globals={"args": args, "kwargs": kwargs, "f": f},
-        num_threads=torch.get_num_threads(),
-    )
-    return f"{(t0.blocked_autorange().mean):.3f}"
-
-
-def generate_csv_dict(
-    pipeline_cls: str, ckpt: str, args: argparse.Namespace, benchmark_info: BenchmarkInfo
-) -> Dict[str, Union[str, bool, float]]:
-    """Packs benchmarking data into a dictionary for latter serialization."""
-    data_dict = {
-        "pipeline_cls": pipeline_cls,
-        "ckpt_id": ckpt,
-        "batch_size": args.batch_size,
-        "num_inference_steps": args.num_inference_steps,
-        "model_cpu_offload": args.model_cpu_offload,
-        "run_compile": args.run_compile,
-        "time (secs)": benchmark_info.time,
-        "memory (gbs)": benchmark_info.memory,
-        "actual_gpu_memory (gbs)": f"{(TOTAL_GPU_MEMORY):.3f}",
-        "github_sha": GITHUB_SHA,
-    }
-    return data_dict
-
-
-def write_to_csv(file_name: str, data_dict: Dict[str, Union[str, bool, float]]):
-    """Serializes a dictionary into a CSV file."""
-    with open(file_name, mode="w", newline="") as csvfile:
-        writer = csv.DictWriter(csvfile, fieldnames=BENCHMARK_FIELDS)
-        writer.writeheader()
-        writer.writerow(data_dict)
-
-
-def collate_csv(input_files: List[str], output_file: str):
-    """Collates multiple identically structured CSVs into a single CSV file."""
-    with open(output_file, mode="w", newline="") as outfile:
-        writer = csv.DictWriter(outfile, fieldnames=BENCHMARK_FIELDS)
-        writer.writeheader()
-
-        for file in input_files:
-            with open(file, mode="r") as infile:
-                reader = csv.DictReader(infile)
-                for row in reader:
-                    writer.writerow(row)

utils/print_env.py

@@ -28,6 +28,16 @@ print("Python version:", sys.version)
 
 print("OS platform:", platform.platform())
 print("OS architecture:", platform.machine())
+try:
+    import psutil
+
+    vm = psutil.virtual_memory()
+    total_gb = vm.total / (1024**3)
+    available_gb = vm.available / (1024**3)
+    print(f"Total RAM:     {total_gb:.2f} GB")
+    print(f"Available RAM: {available_gb:.2f} GB")
+except ImportError:
+    pass
 
 try:
     import torch