Add example

Author: mgoin

examples/example_static_kvcache.py

@@ -0,0 +1,25 @@
+from datasets import load_dataset
+from transformers import AutoTokenizer
+
+from auto_fp8 import AutoFP8ForCausalLM, BaseQuantizeConfig
+
+pretrained_model_dir = "meta-llama/Meta-Llama-3-8B-Instruct"
+quantized_model_dir = "Meta-Llama-3-8B-Instruct-FP8-KV"
+
+tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True)
+tokenizer.pad_token = tokenizer.eos_token
+
+ds = load_dataset("mgoin/ultrachat_2k", split="train_sft").select(range(512))
+examples = [tokenizer.apply_chat_template(batch["messages"], tokenize=False) for batch in ds]
+examples = tokenizer(examples, padding=True, truncation=True, return_tensors="pt").to("cuda")
+
+quantize_config = BaseQuantizeConfig(
+    quant_method="fp8",
+    activation_scheme="static",
+    ignore_patterns=["re:.*lm_head"],
+    kv_cache_quant_targets=("k_proj", "v_proj"),
+)
+
+model = AutoFP8ForCausalLM.from_pretrained(pretrained_model_dir, quantize_config)
+model.quantize(examples)
+model.save_quantized(quantized_model_dir)