Function calling

• Integrate with XGrammar's structural tag: [Feature] Structural tag xgrammar#162, and enable reliable tool use with small models in WebLLM
• Add an E2E MCP-like example, using the structural tag / tool-use stated above

Models

• Support Phi-4 (ongoing)
• Support Gemma3
• Support Gemma3n

Modalities

• Add reliable image input feature (currently have initial support, performance and correctness need to be further investigated)
• Add other modality input (e.g. audio)

Performance

• Profile existing performance, identify bottlenecks and address them if exist
• Switch some existing CPU workload (e.g. sampling) to GPU if performance improves (ongoing: Replace CPU Function Calls with GPU Kernel Invocations  #697)
• Subgroup operation support: Use subgroup operations when possible #553

Others

• Better WASM conversion experience (e.g. hosting a huggingface space, so users do not need to set up environment)
• Qwen2.5's 1.5B webgpu-only correctness issue—very obvious with DeepSeek-R1-Distill
• Parse thinking/non-thinking tokens when returning completion response