[Bug] There is a gap between the acceptance rates of training and inference

### Checklist - [x] 1. I have searched related issues but cannot get the expected help. - [x] 2. The bug has not been fixed in the latest version. - [x] 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback. - [x] 4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/sgl-project/SpecForge/discussions/new/choose Otherwise, it will be closed. - [x] 5. Please use English, otherwise it will be closed. ### Describe the bug I trained a Dflash application using the latest training code for Qwen3.5-4B. The draft configuration for 4B is from the official documentation, while Qwen3.5-4B is a version I fine-tuned using internal data. The task was OCR. This training used 70,000 data points, achieving a 98% acceptance rate during training. <img width="2972" height="822" alt="Image" src="https://github.com/user-attachments/assets/243ba344-1075-46ba-ba28-e673d1db3163" /> I used a version of VLLM that supports Dflash for inference, but the average acceptance rate was only 10%. I've already aligned the chat-template, and I haven't used `<think>` during either training or inference. <img width="1504" height="132" alt="Image" src="https://github.com/user-attachments/assets/9ea744d3-2dc1-4411-880b-9fff60e426b2" /> Are there any gaps I might be overlooking? ### Reproduction ``` BUILD_DATASET_NUM_PROC=64 ATTENTION_BACKEND=${2:-flex_attention} NUM_GPUS=4 # Use patched specforge (fixes circular import in original) CUDA_VISIBLE_DEVICES=0,1,2,3 torchrun \ --standalone \ --nproc_per_node $NUM_GPUS \ $ROOT_DIR/scripts/train_dflash.py \ --target-model-path qwen3.5_4B\ --draft-config-path Qwen3.5-4B-Dflash/config.json \ --train-data-path data_filtered.jsonl\ --output-dir deflash_outputs/qwen3.5-4b-dflash-opc \ --num-epochs 10 \ --batch-size 2 \ --learning-rate 6e-4 \ --warmup-ratio 0.04 \ --max-grad-norm 1.0 \ --max-length 4096 \ --chat-template qwen3.5-nothink \ --attention-backend $ATTENTION_BACKEND \ --num-anchors 512 \ --loss-decay-gamma 7.0 \ --log-interval 50 \ --save-interval 10000 \ --target-model-backend hf \ --block-size 16 \ ``` ### Environment specforge [latest] vllm [0.19.1.rc.0] nightly