import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf", dtype=torch.float16, device_map="auto")
inputs = tokenizer("I like rock music because", return_tensors="pt").to(model.device)

model.generate(**inputs, do_sample=False, max_new_tokens=20, use_cache=False)

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, DynamicCache

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf", dtype=torch.float16, device_map="auto")
inputs = tokenizer("I like rock music because", return_tensors="pt").to(model.device)

past_key_values = DynamicCache(config=model.config)
out = model.generate(**inputs, do_sample=False, max_new_tokens=20, past_key_values=past_key_values)

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf", dtype=torch.float16, device_map="auto")
inputs = tokenizer("Hello, my name is", return_tensors="pt").to(model.device)

out = model.generate(**inputs, do_sample=False, max_new_tokens=20, cache_implementation="static")
tokenizer.batch_decode(out, skip_special_tokens=True)[0]
"Hello, my name is [Your Name], and I am a [Your Profession] with [Number of Years] of"

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-0.6B")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B", device_map="auto")

# leave the inputs on CPU instead of calling .to(model.device).
inputs = tokenizer("The French Bread Law states", return_tensors="pt")

# generate runs forward on the model device but returns the output on the input_ids device.
output = model.generate(**inputs, do_sample=False, max_new_tokens=20)
print(output.device)
cpu

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

ckpt = "microsoft/Phi-3-mini-4k-instruct"
tokenizer = AutoTokenizer.from_pretrained(ckpt)
model = AutoModelForCausalLM.from_pretrained(ckpt, dtype=torch.float16, device_map="auto")
inputs = tokenizer("Fun fact: The shortest", return_tensors="pt").to(model.device)

out = model.generate(**inputs, do_sample=False, max_new_tokens=23, cache_implementation="offloaded")
print(tokenizer.batch_decode(out, skip_special_tokens=True)[0])
Fun fact: The shortest war in history was between Britain and Zanzibar on August 27, 1896.

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from accelerate import Accelerator

def resilient_generate(model, *args, **kwargs):
    oom = False
    device = Accelerator().device
    torch_device_module = getattr(torch, device, torch.cuda)
    try:
        return model.generate(*args, **kwargs)
    except torch.OutOfMemoryError as e:
        print(e)
        print("retrying with cache_implementation='offloaded'")
        oom = True
    if oom:
        torch_device_module.empty_cache()
        kwargs["cache_implementation"] = "offloaded"
        return model.generate(*args, **kwargs)

ckpt = "microsoft/Phi-3-mini-4k-instruct"
tokenizer = AutoTokenizer.from_pretrained(ckpt)
model = AutoModelForCausalLM.from_pretrained(ckpt, dtype=torch.float16, device_map="auto")
prompt = ["okay "*1000 + "Fun fact: The most"]
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
beams = { "num_beams": 40, "num_return_sequences": 20, "max_new_tokens": 23, "early_stopping": True, }
out = resilient_generate(model, **inputs, **beams)
responses = tokenizer.batch_decode(out[:,-28:], skip_special_tokens=True)

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf", dtype=torch.float16, device_map="auto")
inputs = tokenizer("I like rock music because", return_tensors="pt").to(model.device)

out = model.generate(
    **inputs,
    do_sample=False,
    max_new_tokens=20,
    cache_implementation="quantized",
    cache_config={
        "nbits": 4,
        "backend": "hqq",
        "axis_key": 1,
        "axis_value": 1
    }
)
print(tokenizer.batch_decode(out, skip_special_tokens=True)[0])
I like rock music because it's loud and energetic. It's a great way to express myself and rel

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf", dtype=torch.float16, device_map="auto")
inputs = tokenizer("I like rock music because", return_tensors="pt").to(model.device)

out = model.generate(
    **inputs,
    do_sample=False,
    max_new_tokens=20,
    cache_implementation="quantized",
    cache_config={
        "nbits": 4,
        "backend": "quanto",
        "axis_key": 0,
        "axis_value": 0
    }
)
print(tokenizer.batch_decode(out, skip_special_tokens=True)[0])
I like rock music because it's loud and energetic. It's a great way to express myself and rel

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507", dtype=torch.float16, device_map="auto")
inputs = tokenizer("I like rock music because", return_tensors="pt").to(model.device)

out = model.generate(**inputs, do_sample=False, max_new_tokens=20, cache_implementation="quantized", cache_config={"backend": "fp8"})
print(tokenizer.batch_decode(out, skip_special_tokens=True)[0])
I like rock music because it is powerful and emotional. I also like classical music because it is elegant and sophisticated. I enjoy

import torch
from transformers import AutoTokenizer,AutoModelForCausalLM, DynamicCache, StaticCache

model_id = "meta-llama/Llama-2-7b-chat-hf"
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map='auto')
tokenizer = AutoTokenizer.from_pretrained(model_id)

user_prompts = ["Hello, what's your name?", "Btw, yesterday I was on a rock concert."]

past_key_values = DynamicCache(config=model.config)

messages = []
for prompt in user_prompts:
    messages.append({"role": "user", "content": prompt})
    inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)
    input_length = inputs["input_ids"].shape[1]
    outputs = model.generate(**inputs, do_sample=False, max_new_tokens=256, past_key_values=past_key_values)
    completion = tokenizer.decode(outputs[0, input_length: ], skip_special_tokens=True)
    messages.append({"role": "assistant", "content": completion})

# Remove the last three tokens from the cache.
past_key_values.crop(-3)

# Enable this before the forward pass if you need to roll back tokens.
past_key_values.activate_past_recording()

                    cached positions
                    ┌───┬───┬───┬───┬───┬───┐
before crop(-3)     │ 0 │ 1 │ 2 │ 3 │ 4 │ 5 │
                    └───┴───┴───┴───┴───┴───┘
                                ╰─────┬─────╯
                                 rolled back

after crop(-3)
                    ┌───┬───┬───┐
full attention      │ 0 │ 1 │ 2 │    keeps the whole prefix
                    └───┴───┴───┘
                            ┌───┐
sliding_window=2            │ 2 │    keeps sliding_window - 1
                            └───┘

import copy
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, DynamicCache, StaticCache

model_id = "meta-llama/Llama-2-7b-chat-hf"
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map={"": 0})
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Init StaticCache with big enough max-length (1024 tokens for the below example)
# You can also init a DynamicCache, if that suits you better
prompt_cache = StaticCache(config=model.config, max_cache_len=1024)

INITIAL_PROMPT = "You are a helpful assistant. "
inputs_initial_prompt = tokenizer(INITIAL_PROMPT, return_tensors="pt").to(model.device.type)
# This is the common prompt cached, we need to run forward without grad to be able to copy
with torch.no_grad():
     prompt_cache = model(**inputs_initial_prompt, past_key_values = prompt_cache).past_key_values

prompts = ["Help me to write a blogpost about travelling.", "What is the capital of France?"]
responses = []
for prompt in prompts:
    new_inputs = tokenizer(INITIAL_PROMPT + prompt, return_tensors="pt").to(model.device.type)
    past_key_values = copy.deepcopy(prompt_cache)
    outputs = model.generate(**new_inputs, past_key_values=past_key_values,max_new_tokens=20)
    response = tokenizer.batch_decode(outputs)[0]
    responses.append(response)

print(responses)