isHuangXin 3b04140a54 feat: add I2_S GGUF conversion for bitnet-b1.58-2B-4T and refactor T-MAC LUT path ...

- Add quantize_to_i2_s() for direct ternary-to-I2_S packing in conversion script
- Support offline-quantized models (uint8 packed weights + weight_scale)
- Fix weight_quant double-quantization bug for offline-quantized models
- Fix I2_S scale computation to use first nonzero absolute value
- Add I2_S ftype mapping and BitNetForCausalLM registration
- Refactor ggml-bitnet-lut T-MAC wrapper with proper mul_mat implementation
- Update llama.cpp submodule with I2_S ftype and 2B model type support

2026-07-13 06:26:16 +02:00

..

bitnet-lut-kernels.h

feat: add I2_S GGUF conversion for bitnet-b1.58-2B-4T and refactor T-MAC LUT path

2026-07-13 06:26:16 +02:00

gemm-config.h

[fix] embed-quant q6_k; [modify] README update

2026-01-20 04:56:50 +00:00

ggml-bitnet.h

feat: add I2_S GGUF conversion for bitnet-b1.58-2B-4T and refactor T-MAC LUT path

2026-07-13 06:26:16 +02:00

kernel_config.ini

feat: add I2_S GGUF conversion for bitnet-b1.58-2B-4T and refactor T-MAC LUT path

2026-07-13 06:26:16 +02:00