Add NVFP4A16 quantization examples (#1679)

SUMMARY:
"Add NVFP4A16 quantization examples"


TEST PLAN:
"By running the qwen3_example.py file, you can compress the Qwen3-32B
model using the NVFP4A16 compression method."

---------

Co-authored-by: Dipika Sikka <[email protected]>
Co-authored-by: Dipika Sikka <[email protected]>

Author: wangwenmingaa

examples/quantization_w4a16_fp4/qwen3_example.py

@@ -0,0 +1,34 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+from llmcompressor import oneshot
+from llmcompressor.modifiers.quantization import QuantizationModifier
+from llmcompressor.utils import dispatch_for_generation
+
+# Load model.
+MODEL_ID = "Qwen/Qwen3-32B"
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID, torch_dtype="auto", trust_remote_code=True
+)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
+
+# Configure the quantization algorithm and scheme.
+# In this case, we:
+#   * quantize the weights to fp4 with per group 16 via ptq
+recipe = QuantizationModifier(targets="Linear", scheme="NVFP4A16", ignore=["lm_head"])
+
+# Apply quantization.
+oneshot(model=model, recipe=recipe)
+
+print("\n\n========== 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=100)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
+print("==========================================\n\n")
+
+# Save to disk in compressed-tensors format.
+SAVE_DIR = MODEL_ID.rstrip("/").split("/")[-1] + "-NVFP4A16"
+model.save_pretrained(SAVE_DIR, save_compressed=True)
+tokenizer.save_pretrained(SAVE_DIR)