[Qwen3Next] Add FP8 Quantization Example (#1886)

SUMMARY:
Added qwen3 next fp8 quantization example. Model produced is uploaded
[here](https://huggingface.co/shanjiaz/qwen3-80b-fp8-dynamic)


TEST PLAN:
Tested locally.

---------

Signed-off-by: shanjiaz <[email protected]>

Author: shanjiaz

examples/quantization_w8a8_fp8/qwen3_next_example.py

@@ -0,0 +1,45 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+from llmcompressor import oneshot
+from llmcompressor.modifiers.quantization import QuantizationModifier
+from llmcompressor.utils import dispatch_for_generation
+
+MODEL_ID = "Qwen/Qwen3-Next-80B-A3B-Instruct"
+
+# Load model.
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    torch_dtype="auto",
+    low_cpu_mem_usage=True,
+    trust_remote_code=True,
+)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
+
+recipe = QuantizationModifier(
+    targets=["Linear"],
+    scheme="FP8_DYNAMIC",
+    ignore=[
+        "lm_head",
+        "re:.*mlp.gate$",
+        "re:.*mlp.shared_expert_gate$",
+        "re:.*linear_attn.*",
+    ],
+)
+
+# 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.rstrip("/").split("/")[-1] + "-FP8-Dynamic"
+model.save_pretrained(SAVE_DIR, save_compressed=True)
+tokenizer.save_pretrained(SAVE_DIR)