Require distinct Q and K projections in native HRX Qwen fusion

Row: BACKEND-ROCM

The pinned AMD llama.cpp Qwen attention matcher accepts a K projection as both the query and key chain. When a complete graph visits K before Q, it emits one partial Qwen postprocess and leaves the real query to generic RMSNorm and RoPE. match_qwen_attention_postprocess in ggml/src/ggml-hrx/dispatch_registration/qwen/dispatch-qwen-attention-postprocess.cpp:623 does not require distinct query and key projection nodes.

The #3083 implementer owns the in-flow scheduling correction. The reservation helper already rejects this ambiguity, but the actual matcher must enforce the same complete-region invariant. Preserve the original matching and traversal defaults, numerical tolerances, and the complete Qwen fusion.

The CPU regression enters the public dispatch scheduler with BF16 Q16/KV8, token count1, and K-before-Q graph order. It fails at the assertion that a complete Qwen postprocess leaves no generic RMSNorm: exit -6, test ELF 1fe0b0bbf1a22a84fb652816ad943e678e415d167da8bfb9383c3db9afb613a8, unchanged backend fb2301563318df2253bc681272247a2a5587a42921a9b376b89fa103de70b2a9. Evidence: build-hrx-prefill-repair/evidence/key-first-scheduler-red.{json,log} in the #3083 worktree.

The #3083 spec will record this narrow matcher obligation before its implementation. A separate sequential GPU regression currently rejects NaN in the first decode K cache. This issue does not yet attribute that numerical failure to this matcher ambiguity; the operator will rerun it after the scoped correction.

Start in ggml/src/ggml-hrx/dispatch_registration/qwen/dispatch-qwen-attention-postprocess.cpp at match_qwen_attention_postprocess around line 623, then review the key-first scheduler evidence in build-hrx-prefill-repair/evidence/key-first-scheduler-red.{json,log}. Verify the matcher requires distinct query and key projection nodes while preserving the existing defaults and complete fusion, then rerun the CPU regression with BF16 Q16/KV8 and token count 1 to confirm no generic RMSNorm remains.