--- title: Qwen2-VL-72B-Instruct-FP8-dynamic canonical_url: "https://www.modelscope.cn/models/nm-testing/Qwen2-VL-72B-Instruct-FP8-dynamic" md_url: "https://www.modelscope.cn/models/nm-testing/Qwen2-VL-72B-Instruct-FP8-dynamic.md" repository: nm-testing/Qwen2-VL-72B-Instruct-FP8-dynamic last_updated: 2025-04-24 license: apache-2.0 model_type: - qwen2_vl architectures: - Qwen2VLForConditionalGeneration base_model: - Qwen/Qwen2-VL-72B-Instruct base_model_relation: quantized parameters: 73.4B tensor_type: - BF16 - F8_E4M3 library_name: - transformer - safetensors - pytorch frameworks: - pytorch language: - en inference_backends: - "deploy_task vlm/text/emb" - "lmdeploy 0.9.1" - "sglang 0.5.2" - "vllm 0.9.2" downloads: 809 stars: 0 tags: - vllm - vision - w4a16 --- # Qwen2-VL-72B-Instruct-FP8-dynamic > Qwen2-VL-72B-Instruct-FP8-dynamic - nm-testing 在 ModelScope 开源的模型。Qwen2-VL-72B-Instruct-quantized-w4a16 nm-testing/Qwen2-VL-72B-Instruct-FP8-dynamic 是 ModelScope 魔搭社区上的 73.4B 参数机器学习模型，采用 apache-2.0 许可，基于 Qwen/Qwen2-VL-72B-Instruct 构建，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。 - **Repository**: nm-testing/Qwen2-VL-72B-Instruct-FP8-dynamic - **License**: apache-2.0 - **Parameters**: 73.4B - **Base model**: Qwen/Qwen2-VL-72B-Instruct - **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2 - **Tags**: vllm, vision, w4a16 - **Downloads**: 809 - **Stars**: 0 - **Last updated**: 2025-04-24 Source: https://www.modelscope.cn/models/nm-testing/Qwen2-VL-72B-Instruct-FP8-dynamic --- # Qwen2-VL-72B-Instruct-quantized-w4a16 ## Model Overview - **Model Architecture:** Qwen/Qwen2-VL-72B-Instruct - **Input:** Vision-Text - **Output:** Text - **Model Optimizations:** - **Weight quantization:** FP8 - **Activation quantization:** FP8 - **Release Date:** 2/24/2025 - **Version:** 1.0 - **Model Developers:** Neural Magic Quantized version of [Qwen/Qwen2-VL-72B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct). ### Model Optimizations This model was obtained by quantizing the weights of [Qwen/Qwen2-VL-72B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct) to FP8 data type, ready for inference with vLLM >= 0.5.2. ## Deployment ### Use with vLLM This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below. ```python from vllm.assets.image import ImageAsset from vllm import LLM, SamplingParams # prepare model llm = LLM( model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16", trust_remote_code=True, max_model_len=4096, max_num_seqs=2, ) # prepare inputs question = "What is the content of this image?" inputs = { "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n", "multi_modal_data": { "image": ImageAsset("cherry_blossom").pil_image.convert("RGB") }, } # generate response print("========== SAMPLE GENERATION ==============") outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64)) print(f"PROMPT : {outputs[0].prompt}") print(f"RESPONSE: {outputs[0].outputs[0].text}") print("==========================================") ``` vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details. ## Creation This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below as part a multimodal announcement blog.
Model Creation Code ```python from transformers import AutoProcessor, Qwen2VLForConditionalGeneration from llmcompressor.modifiers.quantization import QuantizationModifier from llmcompressor.transformers import oneshot, wrap_hf_model_class MODEL_ID = "Qwen/Qwen2-VL-72B-Instruct" # Load model. model_class = wrap_hf_model_class(Qwen2VLForConditionalGeneration) model = model_class.from_pretrained(MODEL_ID, device_map="auto", torch_dtype="auto") processor = AutoProcessor.from_pretrained(MODEL_ID) # Configure the quantization algorithm and scheme. # In this case, we: # * quantize the weights to fp8 with per channel via ptq # * quantize the activations to fp8 with dynamic per token recipe = QuantizationModifier( targets="Linear", scheme="FP8_DYNAMIC", ignore=["re:.*lm_head", "re:visual.*"], ) # Apply quantization and save to disk in compressed-tensors format. SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8-dynamic" oneshot(model=model, recipe=recipe, output_dir=SAVE_DIR) processor.save_pretrained(SAVE_DIR) # Confirm generations of the quantized model look sane. print("========== SAMPLE GENERATION ==============") input_ids = processor(text="Hello my name is", return_tensors="pt").input_ids.to("cuda") output = model.generate(input_ids, max_new_tokens=20) print(processor.decode(output[0])) print("==========================================") ```
## Evaluation The model was evaluated using [mistral-evals](https://github.com/neuralmagic/mistral-evals) for vision-related tasks and using [lm_evaluation_harness](https://github.com/neuralmagic/lm-evaluation-harness) for select text-based benchmarks. The evaluations were conducted using the following commands:
Evaluation Commands ### Vision Tasks - 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 ``` ### Text-based Tasks #### MMLU ``` lm_eval \ --model vllm \ --model_args pretrained="",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=,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="",dtype=auto,max_model_len=4096,max_gen_toks=2048,max_num_seqs=128,tensor_parallel_size=,gpu_memory_utilization=0.9 \ --tasks mgsm_cot_native \ --apply_chat_template \ --num_fewshot 0 \ --batch_size auto \ --output_path output_dir ```
### Accuracy
Category Metric Qwen/Qwen2-VL-72B-Instruct neuralmagic/Qwen2-VL-72B-Instruct-FP8-Dynamic Recovery (%)
Vision MMMU (val, CoT)
explicit_prompt_relaxed_correctness		 62.11 60.67 97.68%
VQAv2 (val)
vqa_match		 82.51 82.44 99.91%
DocVQA (val)
anls		 95.01 95.10 100.09%
ChartQA (test, CoT)
anywhere_in_answer_relaxed_correctness		 83.40 83.68 100.34%
Mathvista (testmini, CoT)
explicit_prompt_relaxed_correctness		 66.57 67.07 100.75%
Average Score 77.12 77.39 100.35%
Text MGSM (CoT) 68.60 67.78 98.80%
MMLU (5-shot) 82.70 82.60 99.88%
## Inference Performance This model achieves up to 1.84x speedup in single-stream deployment and up to 1.85x speedup in multi-stream asynchronous deployment, depending on hardware and use-case scenario. The following performance benchmarks were conducted with [vLLM](https://docs.vllm.ai/en/latest/) version 0.7.2, and [GuideLLM](https://github.com/neuralmagic/guidellm).
Benchmarking Command ``` guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-FP8-Dynamic --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=,generated_tokens=,images=,width=,height= --max seconds 120 --backend aiohttp_server ```
### Single-stream performance (measured with vLLM version 0.7.2)
Document Visual Question Answering
1680W x 2240H
64/128		 Visual Reasoning
640W x 480H
128/128		 Image Captioning
480W x 360H
0/128
Hardware Number of GPUs Model Average Cost Reduction Latency (s) QPD Latency (s)th> QPD Latency (s) QPD
A100 4 Qwen/Qwen2-VL-72B-Instruct 6.5 77 4.6 110 4.4 113
2 neuralmagic/Qwen2-VL-72B-Instruct-quantized.w8a8 1.85 7.2 139 4.9 206 4.8 211
1 neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 3.32 10.0 202 5.0 398 4.8 419
H100 4 Qwen/Qwen2-VL-72B-Instruct 4.4 66 3.0 97 2.9 99
2 neuralmagic/Qwen2-VL-72B-Instruct-FP8-Dynamic 1.79 4.7 119 3.3 173 3.2 177
1 neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 2.60 6.4 172 4.3 253 4.2 259
**Use case profiles: Image Size (WxH) / prompt tokens / generation tokens **QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025). ### Multi-stream asynchronous performance (measured with vLLM version 0.7.2)
Document Visual Question Answering
1680W x 2240H
64/128		 Visual Reasoning
640W x 480H
128/128		 Image Captioning
480W x 360H
0/128
Hardware Model Average Cost Reduction Maximum throughput (QPS) QPD Maximum throughput (QPS) QPD Maximum throughput (QPS) QPD
A100x4 Qwen/Qwen2-VL-72B-Instruct 0.3 169 1.1 538 1.2 595
neuralmagic/Qwen2-VL-72B-Instruct-quantized.w8a8 1.84 0.6 293 2.0 1021 2.3 1135
neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 2.73 0.6 314 3.2 1591 4.0 2019
H100x4 Qwen/Qwen2-VL-72B-Instruct 0.5 137 1.2 356 1.3 377
neuralmagic/Qwen2-VL-72B-Instruct-FP8-Dynamic 1.70 0.8 236 2.2 623 2.4 669
neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 2.35 1.3 350 3.3 910 3.6 994
**Use case profiles: Image Size (WxH) / prompt tokens / generation tokens **QPS: Queries per second. **QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025).