isHuangXin
425fbbcb75
Update submodule to release-bitnet-embedding-0.6b-270m branch
2026-07-15 10:30:33 +02:00
isHuangXin
1f6a25aeeb
Update llama.cpp submodule to include SafetensorRemote utility classes
2026-07-15 08:47:54 +02:00
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
isHuangXin
69bf64d373
Add bitnet-embeddings-0.6b model adaptation with F16 and I2_S GGUF conversion
...
- Add GGUF conversion tool for bitnet-embeddings-0.6b (safetensors -> F16/I2_S GGUF)
- Add Qwen3 architecture support in llama.cpp submodule with per-projection RMSNorm
- Add I2_S ternary quantization (2-bit packed -1/0/+1) for lossless precision
- Add f16 norm weight support for correct embedding inference
- Guard bitnet-lut-kernels.h include with TL1/TL2 preprocessor checks
- Update llama.cpp submodule to dev-bitnet-embedding-0.6b branch
- Document F16 (from multilingual-e5-0.6b) and I2_S (from bitnet-embeddings-0.6b) conversion process
2026-07-12 04:10:30 +02:00
XSquirrelC
1876a3e889
[merge] submodule llama.cpp
2026-01-27 03:09:32 +00:00
deva100
112f853414
[feat] I2S kernels for weight & activation parallel on Intel & ARM machine; [feat] I2S GEMV & GEMM(llama.cpp); [feat] quantize activation & dequantize embedding(llama.cpp); [fix] compile bug: cannot define __ARM_FEATURE_DOTPROD(llama.cpp)
2025-11-19 07:35:05 +00:00
younesbelkada
765741d80b
update submodule
2025-05-21 11:52:30 +04:00
junhuihe
488dc1e876
Fix model architecture name
2025-04-22 17:28:59 +08:00
potassiummmm
4f2e41a514
add support for bitnet2b_2501 model
2025-03-12 18:16:45 +08:00
potassiummmm
aa39c0cdcc
fix version requirement of transformers pypi package and model list for codegen
2024-12-18 17:54:23 +08:00
younesbelkada
c1892d6818
updated submodule
2024-11-14 14:53:43 +00:00
potassiummmm
bf11a49f11
Add support for ios platform
2024-11-11 15:13:55 +08:00
Eddie-Wang1120
c82b5e6674
update 3rdparty/llama.cpp
2024-10-18 10:08:22 +08:00
potassiummmm
6cfd8831fd
initial commit
2024-10-17 21:21:10 +08:00
isHuangXin