shreyansh26

ncu --list-sets  # The configuration for sets. A set defines a set of sections.
ncu --list-sections  # The configuration for sections. A section defines a set of metrics.
ncu --query-metrics   # All individual metrics.
ncu --query-metrics-mode suffix --metrics <metrics list> # Check various suffixes for a base metric name.

ncu_cli

shreyansh26

from dataclasses import dataclass


@dataclass
class Args:
    vocab_size: int = 129280
    dim: int = 7168
    inter_dim: int = 18432
    moe_inter_dim: int = 2048
    n_layers: int = 61

shreyansh26

import torch
import torch._inductor.config
import time

torch._inductor.config.triton.cudagraphs = False
torch.set_float32_matmul_precision('high')

def bench(f, name=None, iters=100, warmup=5, display=True, profile=False):
    for _ in range(warmup):
        f()

shreyansh26

import math
import torch
import torch.nn as nn
from torch.nn import functional as F


class RelativePositionBias(nn.Module):
    def __init__(self, bidirectional=True, num_buckets=32, max_distance=128, n_heads=2):
        super(RelativePositionBias, self).__init__()
        self.bidirectional = bidirectional

shreyansh26

import numpy as np  # import numpy library
from util.paramInitializer import initialize_parameters  # import function to initialize weights and biases


class LinearLayer:
    """
        This Class implements all functions to be executed by a linear layer
        in a computational graph

        Args: