From 563d5cf881cebd75a07b3b1646d558e0de3aefc8 Mon Sep 17 00:00:00 2001 From: Limitex <76650151+Limitex@users.noreply.github.com> Date: Wed, 12 Nov 2025 23:26:17 +0900 Subject: [PATCH] add: tensorrt package --- poetry.lock | 140 ++++++++++++++++++++++++++++++++++++++++++++++- pyproject.toml | 2 + requirements.txt | 7 +++ 3 files changed, 148 insertions(+), 1 deletion(-) diff --git a/poetry.lock b/poetry.lock index 4bfc38b..0fb5312 100644 --- a/poetry.lock +++ b/poetry.lock @@ -507,6 +507,48 @@ cuda-pathfinder = ">=1.1,<2.0" [package.extras] all = ["cuda-bindings[all] (>=13.0.3,<13.1.0)"] +[[package]] +name = "cuda-toolkit" +version = "13.0.1" +description = "CUDA Toolkit meta-package" +optional = false +python-versions = "*" +groups = ["main"] +files = [ + {file = "cuda_toolkit-13.0.1-py2.py3-none-any.whl", hash = "sha256:fc763424c5f5dde5c865358777928d23aa18a0165d380980bd3a792176188ffa"}, +] + +[package.dependencies] +nvidia-cuda-runtime = {version = "==13.0.88.*", optional = true, markers = "(sys_platform == \"linux\" or sys_platform == \"win32\") and extra == \"cudart\""} + +[package.extras] +all = ["nvidia-cublas (==13.0.2.14.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-cuda-cccl (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-cuda-crt (==13.0.88.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-cuda-culibos (==13.0.85.*) ; sys_platform == \"linux\"", "nvidia-cuda-cupti (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-cuda-cuxxfilt (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-cuda-nvcc (==13.0.88.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-cuda-nvrtc (==13.0.88.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-cuda-opencl (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-cuda-profiler-api (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-cuda-runtime (==13.0.88.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-cuda-sanitizer-api (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-cufft (==12.0.0.61.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-cufile (==1.15.1.6.*) ; sys_platform == \"linux\"", "nvidia-curand (==10.4.0.35.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-cusolver (==12.0.4.66.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-cusparse (==12.6.3.3.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-npp (==13.0.1.2.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-nvfatbin (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-nvjitlink (==13.0.88.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-nvjpeg (==13.0.1.86.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-nvml-dev (==13.0.87.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-nvptxcompiler (==13.0.88.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-nvtx (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\"", "nvidia-nvvm (==13.0.88.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +cccl = ["nvidia-cuda-cccl (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +crt = ["nvidia-cuda-crt (==13.0.88.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +cublas = ["nvidia-cublas (==13.0.2.14.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +cudart = ["nvidia-cuda-runtime (==13.0.88.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +cufft = ["nvidia-cufft (==12.0.0.61.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +cufile = ["nvidia-cufile (==1.15.1.6.*) ; sys_platform == \"linux\""] +culibos = ["nvidia-cuda-culibos (==13.0.85.*) ; sys_platform == \"linux\""] +cupti = ["nvidia-cuda-cupti (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +curand = ["nvidia-curand (==10.4.0.35.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +cusolver = ["nvidia-cusolver (==12.0.4.66.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +cusparse = ["nvidia-cusparse (==12.6.3.3.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +cuxxfilt = ["nvidia-cuda-cuxxfilt (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +npp = ["nvidia-npp (==13.0.1.2.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +nvcc = ["nvidia-cuda-nvcc (==13.0.88.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +nvfatbin = ["nvidia-nvfatbin (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +nvjitlink = ["nvidia-nvjitlink (==13.0.88.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +nvjpeg = ["nvidia-nvjpeg (==13.0.1.86.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +nvml = ["nvidia-nvml-dev (==13.0.87.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +nvptxcompiler = ["nvidia-nvptxcompiler (==13.0.88.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +nvrtc = ["nvidia-cuda-nvrtc (==13.0.88.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +nvtx = ["nvidia-nvtx (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +nvvm = ["nvidia-nvvm (==13.0.88.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +opencl = ["nvidia-cuda-opencl (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +profiler = ["nvidia-cuda-profiler-api (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] +sanitizer = ["nvidia-cuda-sanitizer-api (==13.0.85.*) ; sys_platform == \"linux\" or sys_platform == \"win32\""] + [[package]] name = "decli" version = "0.6.3" @@ -1429,6 +1471,20 @@ files = [ {file = "nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:a961b2f1d5f17b14867c619ceb99ef6fcec12e46612711bcec78eb05068a60ec"}, ] +[[package]] +name = "nvidia-cuda-runtime" +version = "13.0.88" +description = "CUDA Runtime native Libraries" +optional = false +python-versions = ">=3" +groups = ["main"] +markers = "sys_platform == \"linux\" or sys_platform == \"win32\"" +files = [ + {file = "nvidia_cuda_runtime-13.0.88-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8ba16a33998ee3ee2bf11c8f13e36e3ff86a1d6ad165ffeee863d6eabd0b5f67"}, + {file = "nvidia_cuda_runtime-13.0.88-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:422a38f7c739ecbdd3a4b6ec7ed0a1d74db43d8e9bc26685f3d845638922b178"}, + {file = "nvidia_cuda_runtime-13.0.88-py3-none-win_amd64.whl", hash = "sha256:0156cf8f3453025938aab80bcca909506f4e82f1584a17736df7edeba882cc02"}, +] + [[package]] name = "nvidia-cuda-runtime-cu12" version = "12.4.127" @@ -2607,6 +2663,88 @@ mpmath = ">=1.1.0,<1.4" [package.extras] dev = ["hypothesis (>=6.70.0)", "pytest (>=7.1.0)"] +[[package]] +name = "tensorrt" +version = "10.14.1.48.post1" +description = "TensorRT Metapackage" +optional = false +python-versions = "*" +groups = ["main"] +files = [ + {file = "tensorrt-10.14.1.48.post1.tar.gz", hash = "sha256:5aed87c541fcef881f874fb5724eadbe291851fe2152c962b9cba57cafd4872b"}, +] + +[package.dependencies] +tensorrt_cu13 = "10.14.1.48.post1" + +[package.source] +type = "legacy" +url = "https://pypi.nvidia.com" +reference = "nvidia" + +[[package]] +name = "tensorrt-cu13" +version = "10.14.1.48.post1" +description = "A high performance deep learning inference library" +optional = false +python-versions = ">=3.6" +groups = ["main"] +files = [ + {file = "tensorrt_cu13-10.14.1.48.post1.tar.gz", hash = "sha256:f667aee4b4b908520820b824ada7b7168f29e2659aacee2d5ae42139c6cb884e"}, +] + +[package.dependencies] +tensorrt_cu13_bindings = "10.14.1.48.post1" +tensorrt_cu13_libs = "10.14.1.48.post1" + +[package.extras] +numpy = ["numpy"] + +[[package]] +name = "tensorrt-cu13-bindings" +version = "10.14.1.48.post1" +description = "A high performance deep learning inference library" +optional = false +python-versions = "*" +groups = ["main"] +files = [ + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp310-none-manylinux_2_28_x86_64.whl", hash = "sha256:d8f13ac102187c4a45d11cc671f7f7e59a01ec4e4f1c707fb748d30042a49416"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp310-none-manylinux_2_35_aarch64.whl", hash = "sha256:35e34a14411a24fde813471e4ef1882615992ee1e093c5c254f4fca070b98973"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp310-none-win_amd64.whl", hash = "sha256:8f8ee0d11ee6c3f53d80c768dd9a18b75f7325babb3022b549236bb524fc807a"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp311-none-manylinux_2_28_x86_64.whl", hash = "sha256:30e220ec5cd049709270e9c835d2d69ae5b05d5c269fc067e27155d2b1ba8ff5"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp311-none-manylinux_2_35_aarch64.whl", hash = "sha256:31a6f3d8217fa52533aecbe15073114fa26c2f7835d8d3c8b5371b22899c912a"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp311-none-win_amd64.whl", hash = "sha256:83c58af9c32e527567cf4927957126a487d8b89604822c2be2522bf3e348228b"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp312-none-manylinux_2_28_x86_64.whl", hash = "sha256:1a098123ddf9e69629d66320666efbb2e237db76cd4faf715b7377471b9f4275"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp312-none-manylinux_2_35_aarch64.whl", hash = "sha256:e8db2ddd753097b23e13bd29b61e24431db0724f6f143e917ef107a4f58dff43"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp312-none-win_amd64.whl", hash = "sha256:c762c813bcaddf88e0aae43f8fad2b8637d1088818e9684de2f5e17f773592b5"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp313-none-manylinux_2_28_x86_64.whl", hash = "sha256:51928aa2c11c08d4aa5425c60c7d866c088cffccd0f20a4c8addca9de930c603"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp313-none-manylinux_2_35_aarch64.whl", hash = "sha256:4984a8f841843a3b23c743a24c5d517cf2e3b5eb0c7186bd96791f011fd1dab1"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp313-none-win_amd64.whl", hash = "sha256:dd8bc2507717a6894d5ef26a4acad003657f8c8781370f45c5be19623d5587ae"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp38-none-manylinux_2_28_x86_64.whl", hash = "sha256:cf81fe4996643f632d8097a0a62f46adee003cb4a318cb99d27c779abf9d333a"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp38-none-manylinux_2_35_aarch64.whl", hash = "sha256:216d35aa0bba8179ad7bd55eae365886fc1357c1628cac277e4b810de12bec2e"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp38-none-win_amd64.whl", hash = "sha256:6b2e303be873afb36f1f1c1bdd6110e48bb41eb39bda49f2e3dc3d9daf2d4440"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp39-none-manylinux_2_28_x86_64.whl", hash = "sha256:29c0c0fbc2d62ed7b3708865a2bfdb17bfaf27c1de2132e59833c907516ac590"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp39-none-manylinux_2_35_aarch64.whl", hash = "sha256:cefb9a153ccaa88691dcb21b856e4587cf9f809eee2bfdb666b7e4fb2f0bdf64"}, + {file = "tensorrt_cu13_bindings-10.14.1.48.post1-cp39-none-win_amd64.whl", hash = "sha256:14834211ef73482bccc72cea5cee730276e59baccdc0ce46ef7c697e40557bb0"}, +] + +[package.extras] +numpy = ["numpy"] + +[[package]] +name = "tensorrt-cu13-libs" +version = "10.14.1.48.post1" +description = "TensorRT Libraries" +optional = false +python-versions = "*" +groups = ["main"] +files = [ + {file = "tensorrt_cu13_libs-10.14.1.48.post1.tar.gz", hash = "sha256:8ffa01f315276bff7c7dd01bf11415d0c8c21c45012abd42f2878153ba312d76"}, +] + +[package.dependencies] +cuda-toolkit = {version = ">=13,<14", extras = ["cudart"]} + [[package]] name = "termcolor" version = "3.2.0" @@ -3202,4 +3340,4 @@ type = ["pytest-mypy"] [metadata] lock-version = "2.1" python-versions = ">=3.10,<3.15" -content-hash = "12b19e9873629aa7ba0b7cc3ec5a727740bc5d1bc09d75c9a64aa0e61f5e15f6" +content-hash = "344541e8a3c431274a7375537bb08d656b7f43ab2f29238254f8a4de831db7a1" diff --git a/pyproject.toml b/pyproject.toml index 5cace7d..2a08674 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -20,6 +20,7 @@ dependencies = [ "python-dotenv (>=1.2.1,<2.0.0)", "xformers (>=0.0.29.post3,<0.0.30)", "streamdiffusion[tensorrt] @ git+https://github.com/cumulo-autumn/StreamDiffusion.git@b623251dc055e1fd858d53509aa43e09dfc5cdc0", + "tensorrt (>=10.14.1.48.post1,<11.0.0.0)", ] [tool.poetry] @@ -40,6 +41,7 @@ torch = { version = ">=2.6.0,<3.0.0", source = "pytorch-cu124" } torchaudio = { version = ">=2.6.0,<3.0.0", source = "pytorch-cu124" } torchvision = { version = ">=0.21.0,<0.25.0", source = "pytorch-cu124" } xformers = { version = ">=0.0.29.post3,<0.0.30", source = "pytorch-cu124" } +tensorrt = { version = ">=10.14.1.48.post1,<11.0.0.0", source = "nvidia" } [tool.pytest.ini_options] testpaths = ["tests"] diff --git a/requirements.txt b/requirements.txt index fa31227..82bd808 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,3 +1,4 @@ +--extra-index-url https://pypi.nvidia.com --extra-index-url https://download.pytorch.org/whl/cu124 accelerate==1.11.0 ; python_version >= "3.10" and python_version < "3.15" @@ -10,6 +11,7 @@ coloredlogs==15.0.1 ; python_version >= "3.10" and python_version < "3.15" cuda-bindings==13.0.3 ; python_version >= "3.10" and python_version < "3.15" cuda-pathfinder==1.3.2 ; python_version >= "3.10" and python_version < "3.15" cuda-python==13.0.3 ; python_version >= "3.10" and python_version < "3.15" +cuda-toolkit==13.0.1 ; python_version >= "3.10" and python_version < "3.15" dependency-injector==4.48.2 ; python_version >= "3.10" and python_version < "3.15" diffusers==0.24.0 ; python_version >= "3.10" and python_version < "3.15" filelock==3.20.0 ; python_version >= "3.10" and python_version < "3.15" @@ -30,6 +32,7 @@ nvidia-cublas-cu12==12.4.5.8 ; python_version >= "3.10" and python_version < "3. nvidia-cuda-cupti-cu12==12.4.127 ; python_version >= "3.10" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64" nvidia-cuda-nvrtc-cu12==12.4.127 ; python_version >= "3.10" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64" nvidia-cuda-runtime-cu12==12.4.127 ; python_version >= "3.10" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64" +nvidia-cuda-runtime==13.0.88 ; python_version >= "3.10" and python_version < "3.15" and (sys_platform == "linux" or sys_platform == "win32") nvidia-cudnn-cu12==9.1.0.70 ; python_version >= "3.10" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64" nvidia-cufft-cu12==11.2.1.3 ; python_version >= "3.10" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64" nvidia-curand-cu12==10.3.5.147 ; python_version >= "3.10" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64" @@ -55,6 +58,10 @@ safetensors==0.4.5 ; python_version >= "3.10" and python_version < "3.15" setuptools==80.9.0 ; python_version >= "3.12" and python_version < "3.15" streamdiffusion @ git+https://github.com/cumulo-autumn/StreamDiffusion.git@b623251dc055e1fd858d53509aa43e09dfc5cdc0 ; python_version >= "3.10" and python_version < "3.15" sympy==1.13.1 ; python_version >= "3.10" and python_version < "3.15" +tensorrt-cu13-bindings==10.14.1.48.post1 ; python_version >= "3.10" and python_version < "3.15" +tensorrt-cu13-libs==10.14.1.48.post1 ; python_version >= "3.10" and python_version < "3.15" +tensorrt-cu13==10.14.1.48.post1 ; python_version >= "3.10" and python_version < "3.15" +tensorrt==10.14.1.48.post1 ; python_version >= "3.10" and python_version < "3.15" termcolor==3.2.0 ; python_version >= "3.10" and python_version < "3.15" tokenizers==0.22.1 ; python_version >= "3.10" and python_version < "3.15" torch==2.6.0+cu124 ; python_version >= "3.10" and python_version < "3.15"