# Install causal-conv1d (optional, for efficiency)
pip install causal-conv1d>=1.4.0

# Install Mamba
pip install mamba-ssm
# Or both together
pip install mamba-ssm[causal-conv1d]

import torch
from mamba_ssm import Mamba

batch, length, dim = 2, 64, 16
x = torch.randn(batch, length, dim).to("cuda")

model = Mamba(
    d_model=dim,      # Model dimension
    d_state=16,       # SSM state dimension
    d_conv=4,         # Conv1d kernel size
    expand=2          # Expansion factor
).to("cuda")

y = model(x)  # O(n) complexity!
assert y.shape == x.shape

from mamba_ssm.models.mixer_seq_simple import MambaLMHeadModel
from mamba_ssm.models.config_mamba import MambaConfig
import torch

# Configure Mamba-2 LM
config = MambaConfig(
    d_model=1024,           # Hidden dimension
    n_layer=24,             # Number of layers
    vocab_size=50277,       # Vocabulary size
    ssm_cfg=dict(
        layer="Mamba2",     # Use Mamba-2
        d_state=128,        # Larger state for Mamba-2
        headdim=64,         # Head dimension
        ngroups=1           # Number of groups
    )
)

model = MambaLMHeadModel(config, device="cuda", dtype=torch.float16)

# Generate text
input_ids = torch.randint(0, 1000, (1, 20), device="cuda", dtype=torch.long)
output = model.generate(
    input_ids=input_ids,
    max_length=100,
    temperature=0.7,
    top_p=0.9
)

from transformers import AutoTokenizer
from mamba_ssm.models.mixer_seq_simple import MambaLMHeadModel

# Load pretrained model
model_name = "state-spaces/mamba-2.8b"
tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b")  # Use compatible tokenizer
model = MambaLMHeadModel.from_pretrained(model_name, device="cuda", dtype=torch.float16)

# Generate
prompt = "The future of AI is"
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
output_ids = model.generate(
    input_ids=input_ids,
    max_length=200,
    temperature=0.7,
    top_p=0.9,
    repetition_penalty=1.2
)
generated_text = tokenizer.decode(output_ids[0])
print(generated_text)

from mamba_ssm import Mamba

model = Mamba(
    d_model=256,
    d_state=16,      # Smaller state dimension
    d_conv=4,
    expand=2
).to("cuda")

from mamba_ssm import Mamba2

model = Mamba2(
    d_model=256,
    d_state=128,     # Larger state dimension
    d_conv=4,
    expand=2,
    headdim=64,      # Head dimension for multi-head
    ngroups=1        # Parallel groups
).to("cuda")

# Benchmark Mamba
python benchmarks/benchmark_generation_mamba_simple.py \
  --model-name "state-spaces/mamba-2.8b" \
  --prompt "The future of machine learning is" \
  --topp 0.9 --temperature 0.7 --repetition-penalty 1.2

# Benchmark Transformer
python benchmarks/benchmark_generation_mamba_simple.py \
  --model-name "EleutherAI/pythia-2.8b" \
  --prompt "The future of machine learning is" \
  --topp 0.9 --temperature 0.7 --repetition-penalty 1.2

model = MambaLMHeadModel(config, device="cuda", dtype=torch.float16)
model.gradient_checkpointing_enable()  # Enable checkpointing

pip install mamba-ssm --no-build-isolation

pip install causal-conv1d>=1.4.0

from mamba_ssm.models.mixer_seq_simple import MambaLMHeadModel
model = MambaLMHeadModel.from_pretrained("state-spaces/mamba-2.8b")