[FP8 Block Quant] Add Llama4-Scout example (#1838)

Generates:
https://huggingface.co/nm-testing/Llama-4-Scout-17B-16E-Instruct-FP8-BLOCK/tree/main

Author: dsikka

examples/quantization_w8a8_fp8/llama4_fp8_block_example.py

@@ -0,0 +1,47 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+from llmcompressor import oneshot
+from llmcompressor.modeling import replace_modules_for_calibration
+from llmcompressor.modifiers.quantization import QuantizationModifier
+from llmcompressor.utils import dispatch_for_generation
+
+MODEL_ID = "meta-llama/Llama-4-Scout-17B-16E-Instruct"
+
+# Load model.
+model = AutoModelForCausalLM.from_pretrained(MODEL_ID, torch_dtype="auto")
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+model = replace_modules_for_calibration(model)
+# Configure the quantization algorithm and scheme.
+# In this case, we:
+#   * quantize the weights to fp8 with block size 128 via ptq
+#   * quantize the activations to fp8 with dynamic group activations
+recipe = QuantizationModifier(
+    targets="Linear",
+    scheme="FP8_BLOCK",
+    ignore=[
+        "re:.*lm_head",
+        "re:.*self_attn",
+        "re:.*router",
+        "re:vision_model.*",
+        "re:multi_modal_projector.*",
+        "Llama4TextAttention",
+    ],
+)
+
+# Apply quantization.
+oneshot(model=model, recipe=recipe)
+
+# Confirm generations of the quantized model look sane.
+print("========== SAMPLE GENERATION ==============")
+dispatch_for_generation(model)
+input_ids = tokenizer("Hello my name is", return_tensors="pt").input_ids.to(
+    model.device
+)
+output = model.generate(input_ids, max_new_tokens=20)
+print(tokenizer.decode(output[0]))
+print("==========================================")
+
+# Save to disk in compressed-tensors format.
+SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8-BLOCK"
+model.save_pretrained(SAVE_DIR)
+tokenizer.save_pretrained(SAVE_DIR)