# Install PyTorch
pip install torch --upgrade --extra-index-url https://download.pytorch.org/whl/cu121

# Install dependencies
pip install pytorch-lightning==1.9.5 deepspeed wandb ninja --upgrade

# Install RWKV
pip install rwkv

import os
from rwkv.model import RWKV

os.environ["RWKV_JIT_ON"] = '1'
os.environ["RWKV_CUDA_ON"] = '1'  # Use CUDA kernel for speed

# Load model
model = RWKV(
    model='/path/to/RWKV-4-Pile-1B5-20220903-8040',
    strategy='cuda fp16'
)

# GPT mode (parallel processing)
out, state = model.forward([187, 510, 1563, 310, 247], None)
print(out.detach().cpu().numpy())  # Logits

# RNN mode (sequential processing, same result)
out, state = model.forward([187, 510], None)  # First 2 tokens
out, state = model.forward([1563], state)      # Next token
out, state = model.forward([310, 247], state)  # Last tokens
print(out.detach().cpu().numpy())  # Same logits as above!

from rwkv.model import RWKV
from rwkv.utils import PIPELINE

model = RWKV(model='RWKV-4-Pile-14B-20230313-ctx8192-test1050', strategy='cuda fp16')
pipeline = PIPELINE(model, "20B_tokenizer.json")

# Initial prompt
prompt = "The future of AI is"
state = None

# Generate token by token
for token in prompt:
    out, state = pipeline.model.forward(pipeline.encode(token), state)

# Continue generation
for _ in range(100):
    out, state = pipeline.model.forward(None, state)
    token = pipeline.sample_logits(out)
    print(pipeline.decode(token), end='', flush=True)

model = RWKV(model='RWKV-4-Pile-14B', strategy='cuda fp16')

# Process very long document
state = None
long_document = load_document()  # e.g., 1M tokens

# Stream through entire document
for chunk in chunks(long_document, chunk_size=1024):
    out, state = model.forward(chunk, state)

# State now contains information from entire 1M token document
# Memory usage: O(1) (constant, not O(n)!)

# Training script
import pytorch_lightning as pl
from rwkv.model import RWKV
from rwkv.trainer import RWKVTrainer

# Configure model
config = {
    'n_layer': 24,
    'n_embd': 1024,
    'vocab_size': 50277,
    'ctx_len': 1024
}

# Setup trainer
trainer = pl.Trainer(
    accelerator='gpu',
    devices=8,
    precision='bf16',
    strategy='deepspeed_stage_2',
    max_epochs=1
)

# Train
model = RWKV(config)
trainer.fit(model, train_dataloader)

# Transformer (GPT)
# Memory: O(n²) for attention
# KV cache: 1M × hidden_dim × n_layers × 2 (keys + values)
# Example: 1M × 4096 × 24 × 2 = ~400GB (impractical!)

# RWKV
# Memory: O(1) per token
# State: hidden_dim × n_layers = 4096 × 24 = ~400KB
# 1,000,000× more efficient!

# Transformer: O(n) per token (quadratic overall)
# First token: 1 computation
# Second token: 2 computations
# ...
# 1000th token: 1000 computations

# RWKV: O(1) per token (linear overall)
# Every token: 1 computation
# 1000th token: 1 computation (same as first!)

trainer = pl.Trainer(
    strategy='deepspeed_stage_3',  # Full ZeRO-3
    precision='bf16'
)

os.environ["RWKV_CUDA_ON"] = '1'

model = RWKV(
    model='/absolute/path/to/model.pth',
    strategy='cuda fp16'  # Or 'cpu fp32' for CPU
)

# WRONG: State lost
out1, _ = model.forward(tokens1, None)
out2, _ = model.forward(tokens2, None)  # No context from tokens1!

# CORRECT: State preserved
out1, state = model.forward(tokens1, None)
out2, state = model.forward(tokens2, state)  # Has context from tokens1