Qwen2.5 VL 72B Instruct FP8 Dynamic

import requests
import torch
from PIL import Image
from transformers import AutoProcessor
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import (
    TraceableQwen2_5_VLForConditionalGeneration,
)
from llmcompressor.modifiers.quantization import QuantizationModifier

# Load model.
model_id = Qwen/Qwen2.5-VL-72B-Instruct
model = TraceableQwen2_5_VLForConditionalGeneration.from_pretrained(
    model_id, device_map="auto", torch_dtype="auto"
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Recipe
recipe = [
    QuantizationModifier(
        targets="Linear",
        scheme="FP8_DYNAMIC",
        sequential_targets=["MistralDecoderLayer"],
        ignore=["re:.*lm_head", "re:vision_tower.*", "re:multi_modal_projector.*"],
    ),
]

SAVE_DIR=f"{model_id.split('/')[1]}-FP8-Dynamic"

# Perform oneshot
oneshot(
    model=model,
    recipe=recipe,
    trust_remote_code_model=True,
    output_dir=SAVE_DIR
)

ビジョンタスク

• vqav2
• docvqa
• mathvista
• mmmu
• chartqa

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

テキストベースのタスク

MMLU

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

MGSM

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,max_model_len=4096,max_gen_toks=2048,max_num_seqs=128,tensor_parallel_size=<n>,gpu_memory_utilization=0.9 \
  --tasks mgsm_cot_native \
  --apply_chat_template \
  --num_fewshot 0 \
  --batch_size auto \
  --output_path output_dir