# Docker (recommended)
docker run --gpus all -it --rm nvcr.io/nvidia/pytorch:25.04-py3

# Or pip
pip install megatron-core

# Train with 2 GPUs using data parallelism
torchrun --nproc_per_node=2 examples/run_simple_mcore_train_loop.py

# Or LLaMA-3 8B training
./examples/llama/train_llama3_8b_fp8.sh

LLaMA Training Setup:
- [ ] Step 1: Choose parallelism configuration
- [ ] Step 2: Configure training hyperparameters
- [ ] Step 3: Launch distributed training
- [ ] Step 4: Monitor performance metrics

#!/bin/bash
# train_llama_70b.sh

GPUS_PER_NODE=8
NNODES=8  # 64 GPUs total
TP=4      # Tensor parallel
PP=4      # Pipeline parallel
CP=1      # Context parallel

# LLaMA 70B configuration
MODEL_SIZE=70  # Billion parameters
HIDDEN_SIZE=8192
NUM_LAYERS=80
NUM_HEADS=64
SEQ_LENGTH=4096

# Training hyperparameters
MICRO_BATCH=1
GLOBAL_BATCH=1024
LR=3e-4

torchrun \
  --nproc_per_node=$GPUS_PER_NODE \
  --nnodes=$NNODES \
  pretrain_gpt.py \
  --tensor-model-parallel-size $TP \
  --pipeline-model-parallel-size $PP \
  --context-parallel-size $CP \
  --sequence-parallel \
  --num-layers $NUM_LAYERS \
  --hidden-size $HIDDEN_SIZE \
  --num-attention-heads $NUM_HEADS \
  --seq-length $SEQ_LENGTH \
  --max-position-embeddings $SEQ_LENGTH \
  --micro-batch-size $MICRO_BATCH \
  --global-batch-size $GLOBAL_BATCH \
  --lr $LR \
  --train-iters 100000 \
  --lr-decay-style cosine \
  --lr-warmup-iters 2000 \
  --weight-decay 0.1 \
  --clip-grad 1.0 \
  --bf16 \
  --use-mcore-models \
  --transformer-impl transformer_engine \
  --data-path /path/to/data \
  --vocab-file /path/to/vocab.json \
  --merge-file /path/to/merges.txt

# Single node (8 GPUs)
bash train_llama_70b.sh

# Multi-node with SLURM
sbatch --nodes=8 --gpus-per-node=8 train_llama_70b.sh

Model FLOP Utilization (MFU): Target >40% on H100
Throughput: Tokens/sec/GPU
Memory usage: <80GB per GPU for 70B model
Loss: Should decrease steadily

MoE Training:
- [ ] Step 1: Configure expert parallelism
- [ ] Step 2: Set MoE hyperparameters
- [ ] Step 3: Launch training with EP

# Mixtral 8x7B example
TENSOR_PARALLEL=2
PIPELINE_PARALLEL=1
EXPERT_PARALLEL=4  # Split 8 experts across 4 GPUs
DATA_PARALLEL=4

TOTAL_GPUS=$((TENSOR_PARALLEL * PIPELINE_PARALLEL * EXPERT_PARALLEL * DATA_PARALLEL))
# = 2 * 1 * 4 * 4 = 32 GPUs

torchrun \
  --nproc_per_node=8 \
  pretrain_gpt.py \
  --tensor-model-parallel-size 2 \
  --pipeline-model-parallel-size 1 \
  --expert-model-parallel-size 4 \
  --num-experts 8 \
  --moe-router-topk 2 \
  --moe-router-load-balancing-type aux_loss \
  --moe-aux-loss-coeff 0.01 \
  --hidden-size 4096 \
  --num-layers 32 \
  --num-attention-heads 32 \
  --seq-length 4096 \
  --max-position-embeddings 4096 \
  --bf16 \
  --use-mcore-models \
  --transformer-impl transformer_engine \
  --data-path /path/to/data \
  --vocab-file /path/to/vocab.json \
  --merge-file /path/to/merges.txt

Memory without EP: 8 experts × 7B = 56GB per GPU
Memory with EP=4: 2 experts × 7B = 14GB per GPU
Savings: 75% memory reduction

Performance Optimization:
- [ ] Step 1: Enable Flash Attention
- [ ] Step 2: Use FP8 precision (H100)
- [ ] Step 3: Optimize micro-batch size
- [ ] Step 4: Tune parallelism degrees

--use-mcore-models  # Use Megatron Core models
--transformer-impl transformer_engine  # Use Transformer Engine
--sequence-parallel  # Reduce activation memory (use with TP)

--fp8-hybrid  # FP8 mixed precision training
# Transformer Engine handles FP8 automatically

# Start with 1, increase until OOM
for MBS in 1 2 4 8; do
  echo "Testing micro-batch-size=$MBS"
  torchrun ... --micro-batch-size $MBS
done

Tensor Parallel: Use ≤8 (limited by NVLink within node)
Pipeline Parallel: Use for >70B models
Context Parallel: Use for sequences >8K tokens
Data Parallel: Fill remaining GPUs

TP=8 (1 node)
PP=8 (across nodes)
CP=2 (long sequences)
DP=1
Total = 8 × 8 × 2 × 1 = 128 GPUs

# Increase micro-batch
--micro-batch-size 4  # Was 1

# Enable optimizations
--use-flash-attn
--sequence-parallel

# Reduce TP if >8
--tensor-model-parallel-size 4  # Was 16

--tensor-model-parallel-size 2  # Split model across GPUs
--recompute-granularity full  # Gradient checkpointing
--recompute-method block  # Checkpoint transformer blocks
--recompute-num-layers 1  # Checkpoint every layer

--cpu-optimizer  # Offload optimizer to CPU
--cpu-optimizer-type ADAM  # CPU Adam variant

--lr-warmup-iters 2000  # Longer warmup
--clip-grad 1.0  # Gradient clipping
--init-method-std 0.006  # Smaller init
--attention-dropout 0.0  # No dropout in attention
--hidden-dropout 0.0  # No dropout in FFN