Optimize speculative decoding performance by increasing max_num_batched_tokens to 4096

Upgrade to vllm 0.12.0 and restore original performance arguments for Qwen 3.5 support

Remove limit-mm-per-prompt argument to bypass vLLM 0.8.0 multimodal registration check

Remove speculative-config argument for vLLM 0.8.0 CLI parser

Fix limit-mm-per-prompt syntax for vLLM 0.8.0 CLI parser

Fix: Upgrade to vLLM 0.22.0 and PyTorch 2.11.0 on CUDA 12.4 for native Qwen 3.5 support and host compatibility

Fix: Remove speculative-config argument for vLLM 0.7.2 CLI compliance

Fix: Update --limit-mm-per-prompt format to KEY=VALUE format image=99 for vLLM 0.7.2

Fix: Align vLLM arguments with model card recommendations (chat format, MTP speculative config, limit-mm-per-prompt)

Fix: Remove limit-mm-per-prompt and mm-processor-kwargs for vLLM 0.7.2 compatibility

Fix: Update --limit-mm-per-prompt format to KEY=VALUE for vLLM 0.7.2 compatibility

Fix: Remove show_copy_button parameter from gr.Textbox for Gradio 6 compatibility

Initial commit: NuExtract3 Gradio space setup powered by vLLM on A100 GPU