[perf] FastH3 two-Spark: gather packed FP4 inputs before head projections

Opt-in h3_vsa_fp4.sp_input_gather (default false; requires sp_projection_overlap) gathers the
already-packed FP4 inputs and rotary tables, then computes each rank's assigned Q/K/V heads locally;
the gate projection overlaps the smaller transfer. Supported on the measured GB10/cuDNN shape only;
other shapes keep the existing exchange. Enabled in the Spark-pair example.
T2AV on 2 Sparks: 19.35 -> 18.76 s/clip (merge gate check, same SP reduction order rules).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

examples/inference/basic/basic_fasth3_spark_pair_qad_v2_nvfp4.yaml

@@ -52,6 +52,7 @@ generator:
         sp_pooled_key_mean: true
         sp_direct_keys: true
         sp_projection_overlap: true
+        sp_input_gather: true
       VSA_sparsity: 0.8
       VSA_tile_size: 64
       h3_sequential_load: false