Rate This Document
Findability
Accuracy
Completeness
Readability

What's New

The following tables describe the latest updates in documents of BoostSRA. New features are released after being verified.

April 2026

No.

Update

Description

Document

1

Migrated the KBest documents to the GitCode open-source platform.

Binary software packages and documents are provided on GitCode.

BoostSRA KBest documents

2

Migrated the KScaNN documents to the GitCode open-source platform.

Binary software packages and documents are provided on GitCode.

BoostSRA KScaNN documents

3

Migrated the KVecTurbo documents to the GitCode open-source platform.

Open-source software packages and documents are provided on GitCode.

BoostSRA KVecTurbo documents

4

Migrated the KNewPfordelta documents to the GitCode open-source platform.

Patch packages and documents for the open-source PForDelta algorithm are provided on GitCode.

BoostSRA KNewPfordelta documents

5

Migrated the Kunpeng hnswlib documents to the GitCode open-source platform.

  • Patch packages and documents for the open-source hnswlib algorithm are provided on GitCode.
  • Supports the FP 16 data type, NEON vectorization, prefetching, and database ID renumbering optimization. The reconstructed hnswlib simplifies the code structure and improves usability.

BoostSRA Kunpeng hnswlib documents

6

Migrated the Kunpeng Faiss documents to the GitCode open-source platform.

  • Patch packages and documents for the open-source Faiss algorithm are provided on GitCode.
  • Provides non-equivalence optimization patch and equivalence optimization patch. The non-equivalence optimization patch further optimizes the IVFPQ algorithm and supports the HNSW FP16 interface.

BoostSRA Faiss documents

7

Added Kunpeng RaBitQ.

  • Intrusive modifications are made to the open-source RaBitQ codebase. This extends its support to the AArch64 architecture, introducing performance optimizations and functional enhancements. The optimizations include FP16 precision optimization, NEON SIMD vectorization, assembly-level Lookup Table (LUT) acceleration, Spilling with Orthogonality-Amplified Residuals (SOAR) spilled vector assignment, and ML-based adaptive nprobe.
  • Patch packages and documents for the open-source RaBitQ are provided on GitCode.

BoostSRA Kunpeng RaBitQ documents

8

Migrated the KRL documents to the GitCode open-source platform.

  • Binary software packages and documents are provided on GitCode.

BoostSRA KRL documents

9

Migrated the Kunpeng TensorFlow inference optimization documents to the GitCode open-source platform.

  • The TensorFlow Serving thread scheduling optimization and the TensorFlow Serving ANNC graph compilation optimization are collectively referred to as "Kunpeng TensorFlow inference optimization."
  • Patch packages and documents for the open-source TensorFlow are provided on GitCode.

BoostSRA TensorFlow inference optimization documents