just use Numpy and u have your 250 million or more keys/second.

u need a lot of RAM.

import time
import hashlib
from coincurve import PrivateKey
from Crypto.Hash import RIPEMD160
import psutil
import os
import signal
import sys
import multiprocessing as mp
from bloom_filter2 import BloomFilter
from google.colab import drive

# Mount Google Drive
drive.mount('/content/drive')

# Config
File_NAME = "Puzzle 71.013.000.csv"
DRIVE_FOLDER = "/content/drive/MyDrive/Puzzle71"
file_path = f"{DRIVE_FOLDER}/{File_NAME}"
SCAN_RANGE = 100_000
TARGET_PREFIX = "f6f543"
BLOOM_CAPACITY = 1_000_000
BLOOM_ERROR_RATE = 0.001

# Load known H160 hashes into Bloom filter
KNOWN_H160S = [
    "f6f5431d25bbf7b12e8add9af5e3475c44a0a5b8",
]
bloom = BloomFilter(max_elements=BLOOM_CAPACITY, error_rate=BLOOM_ERROR_RATE)
for h in KNOWN_H160S:
    bloom.add(h)

# Read decimal numbers from CSV
with open(file_path, 'r') as f:
    lines = [line.strip() for line in f if line.strip()]
if lines[0].lower().startswith('value'):
    lines = lines[1:]
Decimal_numbers = [int(line) for line in lines]

def privatekey_to_h160(priv_key_int):
    try:
        priv = PrivateKey.from_int(priv_key_int)
        pubkey = priv.public_key.format(compressed=True)
        sha256 = hashlib.sha256(pubkey).digest()
        ripemd160 = RIPEMD160.new(sha256).digest()
        return ripemd160.hex()
    except Exception:
        return None

def optimize_performance():
    try:
        p = psutil.Process()
        if hasattr(p, "cpu_affinity"):
            p.cpu_affinity(list(range(os.cpu_count())))
        if hasattr(psutil, "REALTIME_PRIORITY_CLASS"):
            p.nice(psutil.REALTIME_PRIORITY_CLASS)
        else:
            p.nice(-20)
    except Exception as e:
        print(f"[!] Optimization warning: {e}")

def signal_handler(sig, frame):
    print("\n[!] Interrupted. Exiting.")
    sys.exit(0)

def check_key(k):
    h160 = privatekey_to_h160(k)
    if h160 and (h160.startswith(TARGET_PREFIX) or h160 in bloom):
        return ('match', k, h160)
    return ('progress', k, h160)

def process_decimal(decimal):
    start = max(1, decimal - SCAN_RANGE)
    end = decimal + SCAN_RANGE
    keys = list(range(start, end + 1))

    processed = 0
    start_time = time.time()
    last_key = None
    last_h160 = None

    ctx = mp.get_context("fork")
    with ctx.Pool(processes=os.cpu_count()) as pool:
        result_iter = pool.imap_unordered(check_key, keys, chunksize=1000)

        for result in result_iter:
            if result[0] == 'match':
                _, key, h160 = result
                print(f"\n**PREFIX MATCH FOUND!** Private key {hex(key)} produces Hash160: {h160}\n")
            elif result[0] == 'progress':
                _, key, h160 = result
                processed += 1
                last_key = key
                last_h160 = h160

    elapsed = time.time() - start_time
    speed = processed / elapsed if elapsed > 0 else 0
    print(f"\nHash160 of the last processed key {hex(last_key)} -> {last_h160}")
    print(f"[✓] Completed Decimal: {Decimal} - Processed {processed} keys in {elapsed:.2f}s (Speed: {speed:.2f} keys/sec)")

def main():
    signal.signal(signal.SIGINT, signal_handler)
    optimize_performance()

    print(f"\nLoaded {len(Decimal_numbers)} Decimal numbers.")
    print(f"Scanning ±{SCAN_RANGE} around each.\nTarget prefix: {TARGET_PREFIX}")
    print(f"Bloom filter contains {len(KNOWN_H160S)} known H160 hashes.\n")

    for decimal in decimal_numbers:
        process_decimal(decimal)

if __name__ == '__main__':
    main()


Help me out to use rotor cuda gpu modules able run on colab
Private key to hash 160