mirror of
https://github.com/ruvnet/RuVector.git
synced 2026-05-30 12:13:34 +00:00
Add bitnet/ module with absmean ternary quantizer, TernaryTensor type, BITNET_T158 dequantization, and comprehensive test suite (~1600 lines). Components: - quantizer.rs: PtBitnetConfig, absmean_ternary(), quantize_tensor() - ternary_tensor.rs: TernaryTensor, pack/unpack 2-bit ternary encoding - dequantize.rs: dequantize_bitnet_t158(), block dequant, error metrics - tests.rs: Packing roundtrips, quantization correctness, edge cases - gguf/quantization.rs: BitnetT158 = 30 enum variant, block_size, bytes Implements AD-1 (weight representation), AD-5 (GGUF extension), AD-18 (PT-BitNet quantization) from ADR-017. https://claude.ai/code/session_011nTcGcn49b8YKJRVoh4TaK |
||
|---|---|---|
| .. | ||
| attention-exotic-ai-autonomous-systems.md | ||
| bitnet-quantizer-module-design.md | ||
| coherence-engine-ddd.md | ||
| LLM-Integration-Architecture.md | ||
| NPM_PACKAGE_ARCHITECTURE.md | ||
| ruvltra-medium-architecture.md | ||
| SYSTEM_OVERVIEW.md | ||
| TECHNICAL_PLAN.md | ||