Download Latest Version chatglm_cpp-0.4.2.tar.gz (5.8 MB)
Email in envelope

Get an email when there's a new version of ChatGLM.cpp

Home / v0.4.0
Name Modified Size InfoDownloads / Week
Parent folder
chatglm_cpp-0.4.0.tar.gz 2024-06-21 5.7 MB
0
chatglm_cpp-0.4.0-cp312-cp312-win_amd64.whl 2024-06-21 728.5 kB
0
chatglm_cpp-0.4.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl 2024-06-21 1.4 MB
0
chatglm_cpp-0.4.0-cp312-cp312-macosx_11_0_arm64.whl 2024-06-21 1.1 MB
0
chatglm_cpp-0.4.0-cp312-cp312-macosx_10_9_x86_64.whl 2024-06-21 1.2 MB
0
chatglm_cpp-0.4.0-cp311-cp311-win_amd64.whl 2024-06-21 728.9 kB
0
chatglm_cpp-0.4.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl 2024-06-21 1.4 MB
0
chatglm_cpp-0.4.0-cp311-cp311-macosx_11_0_arm64.whl 2024-06-21 1.1 MB
0
chatglm_cpp-0.4.0-cp311-cp311-macosx_10_9_x86_64.whl 2024-06-21 1.2 MB
0
chatglm_cpp-0.4.0-cp310-cp310-win_amd64.whl 2024-06-21 727.8 kB
0
chatglm_cpp-0.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl 2024-06-21 1.4 MB
0
chatglm_cpp-0.4.0-cp310-cp310-macosx_11_0_arm64.whl 2024-06-21 1.1 MB
0
chatglm_cpp-0.4.0-cp310-cp310-macosx_10_9_x86_64.whl 2024-06-21 1.2 MB
0
chatglm_cpp-0.4.0-cp39-cp39-win_amd64.whl 2024-06-21 723.6 kB
0
chatglm_cpp-0.4.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl 2024-06-21 1.4 MB
0
chatglm_cpp-0.4.0-cp39-cp39-macosx_11_0_arm64.whl 2024-06-21 1.1 MB
0
chatglm_cpp-0.4.0-cp39-cp39-macosx_10_9_x86_64.whl 2024-06-21 1.2 MB
0
chatglm_cpp-0.4.0-cp38-cp38-win_amd64.whl 2024-06-21 727.8 kB
0
chatglm_cpp-0.4.0-cp38-cp38-macosx_11_0_arm64.whl 2024-06-21 1.1 MB
0
chatglm_cpp-0.4.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl 2024-06-21 1.4 MB
0
chatglm_cpp-0.4.0-cp38-cp38-macosx_10_9_x86_64.whl 2024-06-21 1.2 MB
0
chatglm_cpp-0.4.0-cp37-cp37m-win_amd64.whl 2024-06-21 726.8 kB
0
chatglm_cpp-0.4.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl 2024-06-21 1.4 MB
0
chatglm_cpp-0.4.0-cp37-cp37m-macosx_10_9_x86_64.whl 2024-06-21 1.2 MB
0
README.md 2024-06-21 479 Bytes
0
v0.4.0 source code.tar.gz 2024-06-21 1.4 MB
0
v0.4.0 source code.zip 2024-06-21 1.5 MB
0
Totals: 27 Items   33.9 MB 0
  • Dynamic memory allocation on demand to fully utilize device memory. No preset scratch size or memory size any more.
  • Drop Baichuan/InternLM support since they were integrated in llama.cpp.
  • API change:
  • CMake CUDA option: -DGGML_CUBLAS changed to -DGGML_CUDA
  • CMake CUDA architecture: -DCUDA_ARCHITECTURES changed to -DCMAKE_CUDA_ARCHITECTURES
  • num_threads in GenerationConfig was removed: the optimal thread settings will be automatically selected.
Source: README.md, updated 2024-06-21