Blame: Makefile - abetlen/llama-cpp-python

Python bindings for llama.cpp

0 0 1 Python

Add makefile 2023-05-26 17:56:20 -04:00			`update:`
			`poetry install`
			`git submodule update --init --recursive`

			`update.vendor:`
			`cd vendor/llama.cpp && git pull origin master`

Migrate to scikit-build-core. Closes #489 2023-07-18 18:52:29 -04:00			`deps:`
Upgrade pip for editable installs 2023-09-14 02:01:45 -04:00			`python3 -m pip install --upgrade pip`
Migrate to scikit-build-core. Closes #489 2023-07-18 18:52:29 -04:00			`python3 -m pip install -e ".[all]"`

Add makefile 2023-05-26 17:56:20 -04:00			`build:`
Update makefile 2024-01-19 08:47:56 -05:00			`python3 -m pip install --verbose -e .`
Add makefile 2023-05-26 17:56:20 -04:00
ci: add debug build to dev makefile 2024-02-21 11:04:30 -05:00			`build.debug:`
misc: Update debug build to keep all debug symbols for easier gdb debugging 2024-05-28 22:52:28 -04:00			`python3 -m pip install \`
			`--verbose \`
			`--config-settings=cmake.verbose=true \`
			`--config-settings=logging.level=INFO \`
			`--config-settings=install.strip=false \`
			`--config-settings=cmake.args="-DCMAKE_BUILD_TYPE=Debug;-DCMAKE_C_FLAGS='-ggdb -O0';-DCMAKE_CXX_FLAGS='-ggdb -O0'" \`
			`--editable .`
ci: add debug build to dev makefile 2024-02-21 11:04:30 -05:00
misc: Update development Makefile 2024-12-06 07:36:47 -05:00			`build.debug.extra:`
			`python3 -m pip install \`
			`--verbose \`
			`--config-settings=cmake.verbose=true \`
			`--config-settings=logging.level=INFO \`
			`--config-settings=install.strip=false \`
			`--config-settings=cmake.args="-DCMAKE_BUILD_TYPE=Debug;-DCMAKE_C_FLAGS='-fsanitize=address -ggdb -O0';-DCMAKE_CXX_FLAGS='-fsanitize=address -ggdb -O0'" \`
			`--editable .`

Add makefile 2023-05-26 17:56:20 -04:00			`build.cuda:`
fix(misc): Update LLAMA_ flags to GGML_ 2024-07-09 00:46:20 -04:00			`CMAKE_ARGS="-DGGML_CUDA=on" python3 -m pip install --verbose -e .`
Add makefile 2023-05-26 17:56:20 -04:00
			`build.openblas:`
fix(misc): Update LLAMA_ flags to GGML_ 2024-07-09 00:46:20 -04:00			`CMAKE_ARGS="-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS" python3 -m pip install --verbose -e .`
Add makefile 2023-05-26 17:56:20 -04:00
			`build.blis:`
fix(misc): Update LLAMA_ flags to GGML_ 2024-07-09 00:46:20 -04:00			`CMAKE_ARGS="-DGGML_BLAS=on -DGGML_BLAS_VENDOR=FLAME" python3 -m pip install --verbose -e .`
Add makefile 2023-05-26 17:56:20 -04:00
Add metal build flags 2023-06-08 00:22:39 -04:00			`build.metal:`
fix(misc): Update LLAMA_ flags to GGML_ 2024-07-09 00:46:20 -04:00			`CMAKE_ARGS="-DGGML_METAL=on" python3 -m pip install --verbose -e .`
Add metal build flags 2023-06-08 00:22:39 -04:00
misc: Add vulkan target 2024-01-29 10:39:23 -05:00			`build.vulkan:`
fix(misc): Update LLAMA_ flags to GGML_ 2024-07-09 00:46:20 -04:00			`CMAKE_ARGS="-DGGML_VULKAN=on" python3 -m pip install --verbose -e .`
misc: Add vulkan target 2024-01-29 10:39:23 -05:00
Update llama.cpp 2024-01-30 09:48:09 -05:00			`build.kompute:`
fix(misc): Update LLAMA_ flags to GGML_ 2024-07-09 00:46:20 -04:00			`CMAKE_ARGS="-DGGML_KOMPUTE=on" python3 -m pip install --verbose -e .`
Update llama.cpp 2024-01-30 09:48:09 -05:00
			`build.sycl:`
fix(misc): Update LLAMA_ flags to GGML_ 2024-07-09 00:46:20 -04:00			`CMAKE_ARGS="-DGGML_SYCL=on" python3 -m pip install --verbose -e .`
Update llama.cpp 2024-01-30 09:48:09 -05:00
feat: adding `rpc_servers` parameter to `Llama` class (#1477) * passthru rpc_servers params wip * enable llama rpc by default * convert string to byte * add rpc package * Revert "enable llama rpc by default" This reverts commit 832c6dd56c979514cec5df224bf2d2014dccd790. * update readme * Only set rpc_servers when provided * Add rpc servers to server options --------- Co-authored-by: Andrei Betlen <abetlen@gmail.com> 2024-06-04 22:38:21 +08:00			`build.rpc:`
fix(misc): Update LLAMA_ flags to GGML_ 2024-07-09 00:46:20 -04:00			`CMAKE_ARGS="-DGGML_RPC=on" python3 -m pip install --verbose -e .`
feat: adding `rpc_servers` parameter to `Llama` class (#1477) * passthru rpc_servers params wip * enable llama rpc by default * convert string to byte * add rpc package * Revert "enable llama rpc by default" This reverts commit 832c6dd56c979514cec5df224bf2d2014dccd790. * update readme * Only set rpc_servers when provided * Add rpc servers to server options --------- Co-authored-by: Andrei Betlen <abetlen@gmail.com> 2024-06-04 22:38:21 +08:00
Add makefile 2023-05-26 17:56:20 -04:00			`build.sdist:`
misc: Update development Makefile 2024-12-06 07:36:47 -05:00			`python3 -m build --sdist --verbose`
Add makefile 2023-05-26 17:56:20 -04:00
			`deploy.pypi:`
			`python3 -m twine upload dist/*`

			`deploy.gh-docs:`
			`mkdocs build`
			`mkdocs gh-deploy`

Update llama.cpp 2023-07-06 17:57:56 -04:00			`test:`
misc: Update development Makefile 2024-12-06 07:36:47 -05:00			`python3 -m pytest --full-trace -v`
Update llama.cpp 2023-07-06 17:57:56 -04:00
misc: Add Ruff formatting (#2148) * Add Ruff formatting and safe lint baseline * Update changelog for Ruff setup 2026-03-22 16:12:02 -07:00			`lint:`
			`python3 -m ruff check llama_cpp tests`
			`python3 -m ruff format --check llama_cpp tests`

			`format:`
			`python3 -m ruff check --fix llama_cpp tests`
			`python3 -m ruff format llama_cpp tests`

Add universal docker image 2023-07-07 03:38:51 -04:00			`docker:`
			`docker build -t llama-cpp-python:latest -f docker/simple/Dockerfile .`

			`run-server:`
misc: Update run server command 2024-12-06 07:37:53 -05:00			`python3 -m llama_cpp.server --model ${MODEL}`
Add universal docker image 2023-07-07 03:38:51 -04:00
Add makefile 2023-05-26 17:56:20 -04:00			`clean:`
Revert "Merge pull request #350 from abetlen/migrate-to-scikit-build-core" This reverts commit fb2c5f7fd94e6e7abc714e910a3ee29f824746d0, reversing changes made to 202ed4464bbed08166550e733c5ae71d499a8adb. 2023-06-09 23:23:16 -04:00			`- rm -rf _skbuild`
misc: Update development Makefile 2024-12-06 07:36:47 -05:00			`- rm llama_cpp/lib/*.so`
			`- rm llama_cpp/lib/*.dylib`
			`- rm llama_cpp/lib/*.metal`
			`- rm llama_cpp/lib/*.dll`
			`- rm llama_cpp/lib/*.lib`
Add makefile 2023-05-26 17:56:20 -04:00
			`.PHONY: \`
			`update \`
			`update.vendor \`
			`build \`
			`build.cuda \`
			`build.opencl \`
			`build.openblas \`
			`build.sdist \`
			`deploy.pypi \`
			`deploy.gh-docs \`
misc: Add Ruff formatting (#2148) * Add Ruff formatting and safe lint baseline * Update changelog for Ruff setup 2026-03-22 16:12:02 -07:00			`lint \`
			`format \`
Add universal docker image 2023-07-07 03:38:51 -04:00			`docker \`
fix(misc): Update LLAMA_ flags to GGML_ 2024-07-09 00:46:20 -04:00			`clean`