b68802ff17
[fix] embed-quant q6_k; [modify] README update
2026-01-20 04:56:50 +00:00
35b1c28585
[fix] correct README
2026-01-15 03:44:50 +00:00
53ffe5e92b
[chore] update README
2026-01-15 03:37:16 +00:00
43da5e5f76
[fix] make demo_benchmark.sh more fast
2025-12-23 07:23:14 +00:00
41cc304868
[chore] add some automation bash script for BitNet Tech Report
2025-12-23 06:48:33 +00:00
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
404980eeca
Merge pull request #290 from microsoft/gpu-readme-dev
...
Update readme for gpu kernels
2025-06-03 14:14:20 +08:00
088e607b25
Merge pull request #280 from microsoft/fix-convert-dev
...
Enable conversion from .safetensors checkpoints to gguf files
2025-06-03 13:59:47 +08:00
c1e9a9a237
Update readme for gpu kernels
2025-05-31 21:41:41 +08:00
43e9b2d4a0
Enable conversion from .safetensors checkpoints to gguf files
2025-05-23 16:19:29 +08:00
69a20459f5
Merge pull request #268 from younesbelkada/add-falcon-e-final
...
Add falcon-e support
2025-05-21 16:28:05 +08:00
5c12850ed9
Merge branch 'add-falcon-e-final' of github.com:younesbelkada/BitNet into add-falcon-e-final
2025-05-21 11:53:40 +04:00
765741d80b
update submodule
2025-05-21 11:52:30 +04:00
f314d18863
feat: add also base models
2025-05-21 04:11:07 +04:00
9e9575665e
Merge branch 'microsoft:main' into add-falcon-e-final
2025-05-20 17:05:11 +04:00
70285e0154
Merge pull request #276 from microsoft/readme-dev
...
refine readme for gpu kernel
2025-05-20 16:14:18 +08:00
6197e9feb0
refine readme for gpu kernel
2025-05-20 12:29:56 +08:00
6c2c08f67e
Merge pull request #266 from microsoft/gpu-dev
2025-05-19 12:46:20 +08:00
154c92b704
Init gpu branch
2025-05-19 04:34:00 +00:00
0015ad5201
Update README.md
2025-05-15 18:49:28 +04:00
de371b708d
add falcon-e support
2025-05-14 17:07:05 +04:00
c9e752c9d7
Fix build error with GCC by forcing Clang compiler in CMake on android/aarch64 ( #242 )
...
GCC does not recognize Clang-specific warning flags like
-Wunreachable-code-break and -Wunreachable-code-return, which are passed
by upstream submodules (e.g., ggml). This patch forces CMake to use Clang
via command-line arguments, avoiding the need to patch nested submodules.
This resolves compiler errors without modifying submodule source code.
2025-05-08 16:22:45 +08:00
1792346223
Add run_inference_server.py for Running llama.cpp Built-in Server ( #204 )
...
* Update CMakeLists.txt
I added a CMake option to compile the Llama.cpp server. This update allows us to easily build and deploy the server using BitNet
* Create run_inference_server.py
same as run_inference, but for use with llama.cpp's built in server, for some extra comfort
In particular:
- The build directory is determined based on whether the system is running on Windows or not.
- A list of arguments (`--model`, `-m` etc.) is created.
- The main argument list is parsed and passed to the `subprocess.run()` method to execute the system command.
2025-05-08 16:22:12 +08:00
c17d1c5d77
Merge pull request #212 from microsoft/arch-name-dev
...
Fix model architecture name
2025-04-23 11:20:15 +08:00
488dc1e876
Fix model architecture name
2025-04-22 17:28:59 +08:00
fd9f1d6e46
Merge pull request #176 from microsoft/readme-dev
...
refine readme
2025-04-16 12:35:53 +08:00
874e6bd5fb
refine readme
2025-04-16 04:34:59 +00:00
034b34cb70
Merge pull request #175 from microsoft/readme-dev
...
add third-party demo
2025-04-15 22:42:12 +08:00
71fdd9472f
add third-party demo
2025-04-15 14:36:05 +00:00
1c77bd8966
Update README.md
2025-04-15 17:11:23 +08:00
8f75f99c72
Update README.md ( #172 )
...
add two FAQs for windows build requestions.
2025-04-15 17:07:20 +08:00
0e7dadba1e
Update README.md
2025-04-15 15:24:42 +08:00
fd3f355a0b
update readme and setup script to support official BitNet b1.58 model ( #171 )
...
* update readme and setup file for new model.
* update model file name
---------
Co-authored-by: Yan Xia <yanxia@microsoft.com >
2025-04-15 14:53:56 +08:00
fa854cf8f8
Merge pull request #167 from potassiummmm/bitnet-25
...
add support for bitnet2b_2501 model
2025-04-15 14:27:46 +08:00
09f91066d6
add conversion logic for new model
2025-03-12 18:34:05 +08:00
4f2e41a514
add support for bitnet2b_2501 model
2025-03-12 18:16:45 +08:00
caf17ec438
update README
2025-02-18 21:13:27 +08:00
437b321dcf
Merge pull request #145 from potassiummmm/readme-new-model
...
Update README
2024-12-20 16:22:10 +08:00
d0fc8c9a39
Update README.md
2024-12-20 14:58:53 +08:00
1791e8eb1c
Merge branch 'microsoft:main' into readme-new-model
2024-12-20 14:56:08 +08:00
253954811b
Merge pull request #130 from lfoppiano/patch-1
...
Make the coverage table more readable with both dark and light theme
2024-12-20 14:55:38 +08:00
933e8950bd
Update README.md
2024-12-19 18:47:53 +08:00
b441b76118
Update README.md
2024-12-19 18:35:31 +08:00
fa83380d99
Update README.md
2024-12-19 18:32:54 +08:00
3e19f15cd0
Merge pull request #142 from microsoft/f3-fix-2
...
Fix model name in setup_env.py
2024-12-19 01:21:21 +08:00
c96c2499d6
Fix model name in setup_env.py
2024-12-19 01:20:14 +08:00
e255fef69b
Merge pull request #141 from potassiummmm/f3-fix
...
F3 fix
2024-12-18 21:27:26 +08:00
0a446952e1
fix readme issue and -cnv option issue
2024-12-18 21:20:26 +08:00
aa39c0cdcc
fix version requirement of transformers pypi package and model list for codegen
2024-12-18 17:54:23 +08:00
33ceabed0b
Merge pull request #137 from younesbelkada/f3-changes
...
Feat: Add changes for Falcon3 release
2024-12-18 11:41:20 +08:00
deva100