[Examples] Add an updated llama3.3 model to examples (#1592)

SUMMARY:
- Add a llama 3.3 70b to the `big_models_with_sequential_onloading`
folder to illustrate large model usage with sequential onloading
- Add code details to the ReadMe
- Fix formatting issue

Next Steps:
- Add back an example test testing the example

---------

Co-authored-by: Kyle Sayers <kylesayrs@gmail.com>
Co-authored-by: Brian Dellabetta <brian-dellabetta@users.noreply.github.com>

Author: 3 people

examples/big_models_with_sequential_onloading/README.md

@@ -1,5 +1,5 @@
-## Big Modeling with Sequential Onloading ##
-### What is Sequential Onloading? ###
+# Big Modeling with Sequential Onloading #
+## What is Sequential Onloading? ##
 Sequential onloading is a memory-efficient approach for compressing large language models (LLMs) using only a single GPU. Instead of loading the entire model into memory—which can easily require hundreds of gigabytes—this method loads and compresses one layer at a time. The outputs are offloaded before the next layer is processed, dramatically reducing peak memory usage while maintaining high compression fidelity.
 
 <p align="center">
@@ -8,5 +8,38 @@ Sequential onloading is a memory-efficient approach for compressing large langua
 
 For more information, see the [RedHat AI blog post](https://developers.redhat.com/articles/2025/05/09/llm-compressor-optimize-llms-low-latency-deployments#generalizing_to_multimodal_and_moe_architectures) or the [LLM Compressor Office Hours Recording](https://www.youtube.com/watch?v=GrhuqQDmBk8).
 
-### Using Sequential Onloading ###
-Sequential onloading is enabled by default within LLM Compressor. To disable sequential onloading, add the `pipeline="basic"` argument to the LLM Compressor `oneshot` function call.
+## Using Sequential Onloading ##
+Sequential onloading is enabled by default within LLM Compressor. To disable sequential onloading, add the `pipeline="basic"` argument to the LLM Compressor `oneshot` function call.
+
+## Running Llama 3.3 70b ##
+The Llama 3.3 70b is larger than 80 GB, surpassing the size of 1 A100. However, with sequential onloading, this model can still be quantized seamlessly using a single GPU.
+
+### Code Walkthough
+
+```python
+model_id = "meta-llama/Llama-3.3-70B-Instruct"
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto")
+```
+
+The model is first loaded onto the `cpu`, as indicated through the use of `None` for the `device_map` argument in the `from_pretrained` method when loading the model.
+
+```python
+oneshot(
+    model=model,
+    dataset=ds,
+    recipe=recipe,
+    max_seq_length=MAX_SEQUENCE_LENGTH,
+    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
+)
+```
+During `oneshot`, only one gpu is required which will be used to onload each layer for calibration in a sequential manner.
+
+```python
+dispatch_for_generation(model)
+sample = tokenizer("Hello my name is", return_tensors="pt")
+sample = {key: value.to("cuda") for key, value in sample.items()}
+output = model.generate(**sample, max_new_tokens=100)
+print(tokenizer.decode(output[0]))
+```
+
+Finally, we call `dispatch_for_generation` to evenly load the model across available devices (potentially offloading the model if required) and run sample generations on the newly quantized model.

examples/big_models_with_sequential_onloading/llama3.3_70b.py

@@ -0,0 +1,83 @@
+from datasets import load_dataset
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+from llmcompressor.modifiers.quantization import GPTQModifier
+from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
+from llmcompressor.transformers import oneshot
+from llmcompressor.utils import dispatch_for_generation
+
+# Select model and load it.
+model_id = "meta-llama/Llama-3.3-70B-Instruct"
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto")
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+# Select calibration dataset.
+DATASET_ID = "HuggingFaceH4/ultrachat_200k"
+DATASET_SPLIT = "train_sft"
+
+# Select number of samples. 512 samples is a good place to start.
+# Increasing the number of samples can improve accuracy.
+NUM_CALIBRATION_SAMPLES = 512
+MAX_SEQUENCE_LENGTH = 2048
+
+# Load dataset and preprocess.
+ds = load_dataset(DATASET_ID, split=f"{DATASET_SPLIT}[:{NUM_CALIBRATION_SAMPLES}]")
+ds = ds.shuffle(seed=42)
+
+
+def preprocess(example):
+    return {
+        "text": tokenizer.apply_chat_template(
+            example["messages"],
+            tokenize=False,
+        )
+    }
+
+
+ds = ds.map(preprocess)
+
+
+# Tokenize inputs.
+def tokenize(sample):
+    return tokenizer(
+        sample["text"],
+        padding=False,
+        max_length=MAX_SEQUENCE_LENGTH,
+        truncation=True,
+        add_special_tokens=False,
+    )
+
+
+ds = ds.map(tokenize, remove_columns=ds.column_names)
+
+# Configure the quantization algorithm to run.
+#   * apply SmoothQuant to make the activations easier to quantize
+#   * quantize the weights to int8 with GPTQ (static per channel)
+#   * quantize the activations to int8 (dynamic per token)
+recipe = [
+    SmoothQuantModifier(smoothing_strength=0.8),
+    GPTQModifier(targets="Linear", scheme="W8A8", ignore=["lm_head"]),
+]
+# Apply algorithms.
+oneshot(
+    model=model,
+    dataset=ds,
+    recipe=recipe,
+    max_seq_length=MAX_SEQUENCE_LENGTH,
+    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
+)
+
+# Confirm generations of the quantized model look sane.
+print("\n\n")
+print("========== SAMPLE GENERATION ==============")
+dispatch_for_generation(model)
+sample = tokenizer("Hello my name is", return_tensors="pt")
+sample = {key: value.to("cuda") for key, value in sample.items()}
+output = model.generate(**sample, max_new_tokens=100)
+print(tokenizer.decode(output[0]))
+print("==========================================\n\n")
+
+# Save to disk compressed.
+SAVE_DIR = model_id.rstrip("/").split("/")[-1] + "-W8A8"
+model.save_pretrained(SAVE_DIR, save_compressed=True)
+tokenizer.save_pretrained(SAVE_DIR)

src/llmcompressor/modifiers/quantization/calibration.py

@@ -77,7 +77,7 @@ def initialize_observer(
             maxshrink=observer_kwargs.get("maxshrink", DEFAULT_MAXSHRINK),
             patience=observer_kwargs.get("patience", DEFAULT_PATIENCE),
             grid=observer_kwargs.get("grid", DEFAULT_GRID),
-            norm=observer_kwargs.get("norm", DEFAULT_NORM)
+            norm=observer_kwargs.get("norm", DEFAULT_NORM),
         )
         module.register_module(f"{base_name}_observer", observer)