https://github.com/vllm-project/llm-compressor/pull/185
from transformers import AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.sparsification import create_sparse_auto_model_class
MODEL_ID = "llava-hf/llava-1.5-7b-hf"
model_class = create_sparse_auto_model_class("LlavaForConditionalGeneration")
model = model_class.from_pretrained(MODEL_ID, device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
recipe = QuantizationModifier(targets="Linear", scheme="FP8_DYNAMIC", ignore=["lm_head"])
oneshot(model=model, recipe=recipe)
# Confirm generations of the quantized model look sane.
print("========== SAMPLE GENERATION ==============")
input_ids = tokenizer("Hello my name is", return_tensors="pt").input_ids.to("cuda")
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-Dynamic"
model.save_pretrained(SAVE_DIR)
tokenizer.save_pretrained(SAVE_DIR)