import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-0.6B")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B", dtype=torch.float16, device_map="auto")
input = tokenizer("The French Bread Law states", return_tensors="pt").to(model.device)

output = model.generate(**input, do_sample=False, max_new_tokens=20, cache_implementation="static")
tokenizer.batch_decode(output, skip_special_tokens=True)[0]

from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B", attn_implementation="flash_attention_2")

import torch
from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen3-0.6B", attn_implementation="kernels-community/flash-attn2"
)

import torch
from transformers import AutoModelForCausalLM, BitsAndBytesConfig

bnb_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16)

model = AutoModelForCausalLM.from_pretrained(
    "allenai/Olmo-3-7B-Think", quantization_config=bnb_config
)

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-0.6B")
model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen3-0.6B", attn_implementation="kernels-community/flash-attn2"
)
inputs = tokenizer("The Le Décret Pain states that a baguette must,", return_tensors="pt")
outputs = model.generate(**inputs, do_sample=False, max_new_tokens=50, cache_implementation="offloaded")

from transformers import AutoModelForCausalLM, DistributedConfig

distributed_config = DistributedConfig(tp_size=4)
model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Meta-Llama-3-8B-Instruct",
    distributed_config=distributed_config,
)
print(model._tp_plan)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import ContinuousBatchingConfig, GenerationConfig

model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen3-0.6B",
    attn_implementation="sdpa",
    device_map="auto",
    torch_dtype=torch.bfloat16,
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-0.6B")

prompts = [
    "The Le Décret Pain states that a baguette must",
    "Explain gravity in one sentence.",
    "Name the capital of France.",
]
inputs = [tokenizer.encode(p) for p in prompts]

generation_config = GenerationConfig(
    max_new_tokens=32,
    eos_token_id=tokenizer.eos_token_id,
    pad_token_id=tokenizer.pad_token_id,
    do_sample=False,
)
continuous_batching_config = ContinuousBatchingConfig(max_batch_tokens=512)

outputs = model.generate_batch(
    inputs=inputs,
    generation_config=generation_config,
    continuous_batching_config=continuous_batching_config,
)

for request_id, output in outputs.items():
    text = tokenizer.decode(output.generated_tokens, skip_special_tokens=True)
    print(f"[{request_id}] {text}")