fix: release SuperKMeans sample buffer after rotation

[marcelo-cjl]

Summary

• release the temporary subsampled training buffer as soon as rotation has populated X_tilde
• avoid retaining that buffer during Forgy initialization and the SuperKMeans iteration loop
• preserve the existing algorithm and rotation-time peak-memory behavior

Memory result

One build run on Cohere 1M x 768 FP32 with SCANN (nlist=1024, sub_dim=2, with_raw_data=false, 16 threads):

• SuperKMeans before this change: 6749.1 MiB average RSS
• SuperKMeans with this change: 6425.4 MiB average RSS
• reduction: 323.7 MiB (4.8% of total average RSS; 8.5% of build RSS above baseline)

The released sample buffer is 768 MiB. The measured reduction is smaller because average RSS is time-weighted over the full build; the buffer is still required during sampling and rotation.

Test plan

• built the AVX2 CPU faiss_test target in Release mode
• faiss_test --gtest_filter='AdSampling.*:PdxLayout.*:BlockL2.*:SuperKMeansAssignIteration.*' (13 tests passed)
• Knowhere vendored integration test for SuperKMeans (3 cases, 44 assertions passed)

Closes #5650

[meta-codesync]

@alibeklfc has imported this pull request. If you are a Meta employee, you can view this in D121294074.

[meta-codesync]

@alibeklfc merged this pull request in 3f08095.