WebGPU: Add indirect dispatch for flash attention graph capture

[feich-ms]

Summary

• Adds PrepareIndirectDispatchProgram to compute dispatch group sizes on GPU from seqlen_k when total_sequence_length is unavailable on CPU
• Extends indirect dispatch to kv_empty layers (shared KV layers where total_sequence_length_=0 would cause dispatch(0) crashes)
• Enables graph capture for models with dynamic sequence lengths (e.g., Gemma4), achieving ~25% decode throughput improvement on WebGPU

Changes

• flash_attention.cc: New PrepareIndirectDispatchProgram::GenerateShaderCode, expanded use_seqlen_k and use_indirect_dispatch conditions, added indirect buffer preparation for kv_empty path
• flash_attention.h: Added PrepareIndirectDispatchProgram class declaration

Test plan

• Verified with Gemma4 INT4 model: ~95-105 tok/s with GC=ON vs ~75 tok/s with GC=OFF
• Tested multiple prompts (short/long) with graph capture enabled — no crashes, correct output
• Verified warmup (capture run) followed by replay produces consistent results

🤖 Generated with Claude Code