01eb415772
Update demo link in README.md
2026-03-10 15:49:46 +08:00
0fdaa16ae3
Merge pull request #421 from microsoft/fix/unsafe-deserialization-gpu-pipeline
...
fix: add weights_only=True to torch.load in GPU inference pipeline
2026-03-09 20:20:21 +08:00
eb60fc39cb
fix: add weights_only=True to torch.load in GPU inference pipeline
...
Mitigate unsafe deserialization vulnerability (CWE-502) in the GPU
inference pipeline. torch.load without weights_only=True allows
arbitrary code execution via malicious pickle payloads in checkpoint
files.
Affected locations:
- gpu/convert_checkpoint.py:37 (checkpoint conversion utility)
- gpu/generate.py:67,69 (fp16 and int2 checkpoint loading)
The utils/ scripts already applied this parameter correctly; this
commit brings the GPU pipeline to the same safety standard.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-09 12:09:19 +00:00
8fd3412fbc
Merge pull request #406 from XsquirrelC/main
...
[fix] convert pt to gguf
2026-02-03 13:30:42 +08:00
3987a503fd
[fix] convert pt to gguf
2026-02-03 05:24:24 +00:00
ade47a535c
Merge pull request #380 from XsquirrelC/main
...
[fix] change README link
2026-01-27 13:48:51 +08:00
77e136fb08
[fix] change README link
2026-01-27 03:39:11 +00:00
cc3c9e4c80
Merge pull request #379 from XsquirrelC/main
...
BitNet CPU Inference Optimization
2026-01-27 11:24:02 +08:00
1876a3e889
[merge] submodule llama.cpp
2026-01-27 03:09:32 +00:00
e8c8107dcf
[modify] some test picture and add power test script
2026-01-25 06:51:33 +00:00
7b2c52b9d5
[modify] some utils test script
2026-01-24 08:40:36 +00:00
2fed9af730
[fix] setup_env.py bug COMPILER_EXTRA_ARGS
2026-01-22 11:11:14 +00:00
7e6f0e14f1
[modify] update README; [feat] some test script in utils
2026-01-22 06:33:03 +00:00
7ea1f2601f
[modify] fine_tuning_result.png
2026-01-20 07:40:37 +00:00
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
Yan Xia