used cuda 12.8

pyproject.toml

@@ -17,11 +17,11 @@ dependencies = [
 ]
 [tool.uv.sources]
 torch = [
-    { index = "pytorch-cpu" },
+    { index = "pytorch-cu128" },
 ]
 [[tool.uv.index]]
-name = "pytorch-cpu"
-url = "https://download.pytorch.org/whl/cpu"
+name = "pytorch-cu128"
+url = "https://download.pytorch.org/whl/cu128"
 explicit = true
 license = { text = "MIT" }
 classifiers = [

uv.lock

@@ -1,10 +1,6 @@
 version = 1
 revision = 2
 requires-python = ">=3.13.3"
-resolution-markers = [
-    "sys_platform != 'darwin'",
-    "sys_platform == 'darwin'",
-]
 
 [[package]]
 name = "accelerate"
@@ -17,8 +13,7 @@ dependencies = [
     { name = "psutil" },
     { name = "pyyaml" },
     { name = "safetensors" },
-    { name = "torch", version = "2.7.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
-    { name = "torch", version = "2.7.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform != 'darwin'" },
+    { name = "torch" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/8a/6e/c29a1dcde7db07f47870ed63e5124086b11874ad52ccd533dc1ca2c799da/accelerate-1.6.0.tar.gz", hash = "sha256:28c1ef1846e690944f98b68dc7b8bb6c51d032d45e85dcbb3adb0c8b99dffb32", size = 363804, upload-time = "2025-04-01T11:53:03.037Z" }
 wheels = [
@@ -53,8 +48,7 @@ version = "0.45.5"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "numpy" },
-    { name = "torch", version = "2.7.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
-    { name = "torch", version = "2.7.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform != 'darwin'" },
+    { name = "torch" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/07/b7/cb5ce4d1a382cf53c19ef06c5fc29e85f5e129b4da6527dd207d90a5b8ad/bitsandbytes-0.45.5-py3-none-manylinux_2_24_x86_64.whl", hash = "sha256:a5453f30cc6aab6ccaac364e6bf51a7808d3da5f71763dffeb6d9694c59136e4", size = 76059261, upload-time = "2025-04-07T13:32:52.573Z" },
@@ -298,6 +292,132 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/63/be/b85e4aa4bf42c6502851b971f1c326d583fcc68227385f92089cf50a7b45/numpy-2.2.5-cp313-cp313t-win_amd64.whl", hash = "sha256:d403c84991b5ad291d3809bace5e85f4bbf44a04bdc9a88ed2bb1807b3360bb8", size = 12750096, upload-time = "2025-04-19T22:47:00.147Z" },
 ]
 
+[[package]]
+name = "nvidia-cublas-cu12"
+version = "12.8.3.14"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/82/df/4b01f10069e23c641f116c62fc31e31e8dc361a153175d81561d15c8143b/nvidia_cublas_cu12-12.8.3.14-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:3f0e05e7293598cf61933258b73e66a160c27d59c4422670bf0b79348c04be44", size = 609620630, upload-time = "2025-01-23T17:55:00.753Z" },
+]
+
+[[package]]
+name = "nvidia-cuda-cupti-cu12"
+version = "12.8.57"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/39/6f/3683ecf4e38931971946777d231c2df00dd5c1c4c2c914c42ad8f9f4dca6/nvidia_cuda_cupti_cu12-12.8.57-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:8e0b2eb847de260739bee4a3f66fac31378f4ff49538ff527a38a01a9a39f950", size = 10237547, upload-time = "2025-01-23T17:47:56.863Z" },
+]
+
+[[package]]
+name = "nvidia-cuda-nvrtc-cu12"
+version = "12.8.61"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d4/22/32029d4583f7b19cfe75c84399cbcfd23f2aaf41c66fc8db4da460104fff/nvidia_cuda_nvrtc_cu12-12.8.61-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:a0fa9c2a21583105550ebd871bd76e2037205d56f33f128e69f6d2a55e0af9ed", size = 88024585, upload-time = "2025-01-23T17:50:10.722Z" },
+]
+
+[[package]]
+name = "nvidia-cuda-runtime-cu12"
+version = "12.8.57"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/16/f6/0e1ef31f4753a44084310ba1a7f0abaf977ccd810a604035abb43421c057/nvidia_cuda_runtime_cu12-12.8.57-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:75342e28567340b7428ce79a5d6bb6ca5ff9d07b69e7ce00d2c7b4dc23eff0be", size = 954762, upload-time = "2025-01-23T17:47:22.21Z" },
+]
+
+[[package]]
+name = "nvidia-cudnn-cu12"
+version = "9.7.1.26"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "nvidia-cublas-cu12" },
+]
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/25/dc/dc825c4b1c83b538e207e34f48f86063c88deaa35d46c651c7c181364ba2/nvidia_cudnn_cu12-9.7.1.26-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:6d011159a158f3cfc47bf851aea79e31bcff60d530b70ef70474c84cac484d07", size = 726851421, upload-time = "2025-02-06T22:18:29.812Z" },
+]
+
+[[package]]
+name = "nvidia-cufft-cu12"
+version = "11.3.3.41"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "nvidia-nvjitlink-cu12" },
+]
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ac/26/b53c493c38dccb1f1a42e1a21dc12cba2a77fbe36c652f7726d9ec4aba28/nvidia_cufft_cu12-11.3.3.41-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:da650080ab79fcdf7a4b06aa1b460e99860646b176a43f6208099bdc17836b6a", size = 193118795, upload-time = "2025-01-23T17:56:30.536Z" },
+]
+
+[[package]]
+name = "nvidia-cufile-cu12"
+version = "1.13.0.11"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e5/9c/1f3264d0a84c8a031487fb7f59780fc78fa6f1c97776233956780e3dc3ac/nvidia_cufile_cu12-1.13.0.11-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:483f434c541806936b98366f6d33caef5440572de8ddf38d453213729da3e7d4", size = 1197801, upload-time = "2025-01-23T17:57:07.247Z" },
+]
+
+[[package]]
+name = "nvidia-curand-cu12"
+version = "10.3.9.55"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/bd/fc/7be5d0082507269bb04ac07cc614c84b78749efb96e8cf4100a8a1178e98/nvidia_curand_cu12-10.3.9.55-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:8387d974240c91f6a60b761b83d4b2f9b938b7e0b9617bae0f0dafe4f5c36b86", size = 63618038, upload-time = "2025-01-23T17:57:41.838Z" },
+]
+
+[[package]]
+name = "nvidia-cusolver-cu12"
+version = "11.7.2.55"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "nvidia-cublas-cu12" },
+    { name = "nvidia-cusparse-cu12" },
+    { name = "nvidia-nvjitlink-cu12" },
+]
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c2/08/953675873a136d96bb12f93b49ba045d1107bc94d2551c52b12fa6c7dec3/nvidia_cusolver_cu12-11.7.2.55-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:4d1354102f1e922cee9db51920dba9e2559877cf6ff5ad03a00d853adafb191b", size = 260373342, upload-time = "2025-01-23T17:58:56.406Z" },
+]
+
+[[package]]
+name = "nvidia-cusparse-cu12"
+version = "12.5.7.53"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "nvidia-nvjitlink-cu12" },
+]
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c2/ab/31e8149c66213b846c082a3b41b1365b831f41191f9f40c6ddbc8a7d550e/nvidia_cusparse_cu12-12.5.7.53-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:3c1b61eb8c85257ea07e9354606b26397612627fdcd327bfd91ccf6155e7c86d", size = 292064180, upload-time = "2025-01-23T18:00:23.233Z" },
+]
+
+[[package]]
+name = "nvidia-cusparselt-cu12"
+version = "0.6.3"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3b/9a/72ef35b399b0e183bc2e8f6f558036922d453c4d8237dab26c666a04244b/nvidia_cusparselt_cu12-0.6.3-py3-none-manylinux2014_x86_64.whl", hash = "sha256:e5c8a26c36445dd2e6812f1177978a24e2d37cacce7e090f297a688d1ec44f46", size = 156785796, upload-time = "2024-10-15T21:29:17.709Z" },
+]
+
+[[package]]
+name = "nvidia-nccl-cu12"
+version = "2.26.2"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/67/ca/f42388aed0fddd64ade7493dbba36e1f534d4e6fdbdd355c6a90030ae028/nvidia_nccl_cu12-2.26.2-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:694cf3879a206553cc9d7dbda76b13efaf610fdb70a50cba303de1b0d1530ac6", size = 201319755, upload-time = "2025-03-13T00:29:55.296Z" },
+]
+
+[[package]]
+name = "nvidia-nvjitlink-cu12"
+version = "12.8.61"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/03/f8/9d85593582bd99b8d7c65634d2304780aefade049b2b94d96e44084be90b/nvidia_nvjitlink_cu12-12.8.61-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:45fd79f2ae20bd67e8bc411055939049873bfd8fac70ff13bd4865e0b9bdab17", size = 39243473, upload-time = "2025-01-23T18:03:03.509Z" },
+]
+
+[[package]]
+name = "nvidia-nvtx-cu12"
+version = "12.8.55"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/8d/cd/0e8c51b2ae3a58f054f2e7fe91b82d201abfb30167f2431e9bd92d532f42/nvidia_nvtx_cu12-12.8.55-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:2dd0780f1a55c21d8e06a743de5bd95653de630decfff40621dbde78cc307102", size = 89896, upload-time = "2025-01-23T17:50:44.487Z" },
+]
+
 [[package]]
 name = "packaging"
 version = "25.0"
@@ -459,8 +579,7 @@ dependencies = [
     { name = "accelerate" },
     { name = "bitsandbytes" },
     { name = "fastapi" },
-    { name = "torch", version = "2.7.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
-    { name = "torch", version = "2.7.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform != 'darwin'" },
+    { name = "torch" },
     { name = "transformers" },
     { name = "uvicorn", extra = ["standard"] },
 ]
@@ -470,7 +589,7 @@ requires-dist = [
     { name = "accelerate", specifier = ">=1.6.0" },
     { name = "bitsandbytes", specifier = ">=0.45.5" },
     { name = "fastapi", specifier = ">=0.115.12" },
-    { name = "torch", specifier = ">=2.7.0", index = "https://download.pytorch.org/whl/cpu" },
+    { name = "torch", specifier = ">=2.7.0", index = "https://download.pytorch.org/whl/cu128" },
     { name = "transformers", specifier = ">=4.51.3" },
     { name = "uvicorn", extras = ["standard"], specifier = ">=0.34.2" },
 ]
@@ -544,48 +663,39 @@ wheels = [
 
 [[package]]
 name = "torch"
-version = "2.7.0"
-source = { registry = "https://download.pytorch.org/whl/cpu" }
-resolution-markers = [
-    "sys_platform == 'darwin'",
-]
-dependencies = [
-    { name = "filelock", marker = "sys_platform == 'darwin'" },
-    { name = "fsspec", marker = "sys_platform == 'darwin'" },
-    { name = "jinja2", marker = "sys_platform == 'darwin'" },
-    { name = "networkx", marker = "sys_platform == 'darwin'" },
-    { name = "setuptools", marker = "sys_platform == 'darwin'" },
-    { name = "sympy", marker = "sys_platform == 'darwin'" },
-    { name = "typing-extensions", marker = "sys_platform == 'darwin'" },
-]
-wheels = [
-    { url = "https://download.pytorch.org/whl/cpu/torch-2.7.0-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:edad98dddd82220465b106506bb91ee5ce32bd075cddbcf2b443dfaa2cbd83bf" },
-    { url = "https://download.pytorch.org/whl/cpu/torch-2.7.0-cp313-none-macosx_11_0_arm64.whl", hash = "sha256:27f5007bdf45f7bb7af7f11d1828d5c2487e030690afb3d89a651fd7036a390e" },
-]
-
-[[package]]
-name = "torch"
-version = "2.7.0+cpu"
-source = { registry = "https://download.pytorch.org/whl/cpu" }
-resolution-markers = [
-    "sys_platform != 'darwin'",
-]
+version = "2.7.0+cu128"
+source = { registry = "https://download.pytorch.org/whl/cu128" }
 dependencies = [
-    { name = "filelock", marker = "sys_platform != 'darwin'" },
-    { name = "fsspec", marker = "sys_platform != 'darwin'" },
-    { name = "jinja2", marker = "sys_platform != 'darwin'" },
-    { name = "networkx", marker = "sys_platform != 'darwin'" },
-    { name = "setuptools", marker = "sys_platform != 'darwin'" },
-    { name = "sympy", marker = "sys_platform != 'darwin'" },
-    { name = "typing-extensions", marker = "sys_platform != 'darwin'" },
+    { name = "filelock" },
+    { name = "fsspec" },
+    { name = "jinja2" },
+    { name = "networkx" },
+    { name = "nvidia-cublas-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-cupti-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-nvrtc-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cudnn-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cufile-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusolver-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusparse-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusparselt-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nccl-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvjitlink-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvtx-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "setuptools" },
+    { name = "sympy" },
+    { name = "triton", marker = "sys_platform == 'linux'" },
+    { name = "typing-extensions" },
 ]
 wheels = [
-    { url = "https://download.pytorch.org/whl/cpu/torch-2.7.0%2Bcpu-cp313-cp313-manylinux_2_28_aarch64.whl" },
-    { url = "https://download.pytorch.org/whl/cpu/torch-2.7.0%2Bcpu-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:3b09aa2c8d30fa567a8d13270fbf9af7ee472fdfafbc7dfdc87c607bf46001f7" },
-    { url = "https://download.pytorch.org/whl/cpu/torch-2.7.0%2Bcpu-cp313-cp313-win_amd64.whl", hash = "sha256:99ca8f4cb53484c45bb668657069c17139c07367ea20ddef2c0ce8412f42da2f" },
-    { url = "https://download.pytorch.org/whl/cpu/torch-2.7.0%2Bcpu-cp313-cp313t-manylinux_2_28_aarch64.whl" },
-    { url = "https://download.pytorch.org/whl/cpu/torch-2.7.0%2Bcpu-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:7b31fa6b1d026542b4ed8ce7ec7ee5489413cd9bd6479c14c5ad559c15d92e3b" },
-    { url = "https://download.pytorch.org/whl/cpu/torch-2.7.0%2Bcpu-cp313-cp313t-win_amd64.whl", hash = "sha256:b42cfe122faed26c6ffee1c97d64e6a1f72a081b64d457a2c97244c1497f4adc" },
+    { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp313-cp313-manylinux_2_28_aarch64.whl" },
+    { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:d2f69f909da5dc52113ec66a851d62079f3d52c83184cf64beebdf12ca2f705c" },
+    { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp313-cp313-win_amd64.whl", hash = "sha256:58c749f52ddc9098155c77d6c74153bb13d8978fd6e1063b5d7b41d4644f5af5" },
+    { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp313-cp313t-manylinux_2_28_aarch64.whl" },
+    { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:78e13c26c38ae92d6841cf9ce760d7e9d52bca3e3183de371812e84274b054dc" },
+    { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp313-cp313t-win_amd64.whl", hash = "sha256:3559e98be824c2b12ab807319cd61c6174d73a524c9961317de8e8a44133c5c5" },
 ]
 
 [[package]]
@@ -621,6 +731,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a9/b6/5257d04ae327b44db31f15cce39e6020cc986333c715660b1315a9724d82/transformers-4.51.3-py3-none-any.whl", hash = "sha256:fd3279633ceb2b777013234bbf0b4f5c2d23c4626b05497691f00cfda55e8a83", size = 10383940, upload-time = "2025-04-14T08:13:43.023Z" },
 ]
 
+[[package]]
+name = "triton"
+version = "3.3.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "setuptools" },
+]
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/7d/74/4bf2702b65e93accaa20397b74da46fb7a0356452c1bb94dbabaf0582930/triton-3.3.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:47bc87ad66fa4ef17968299acacecaab71ce40a238890acc6ad197c3abe2b8f1", size = 156516468, upload-time = "2025-04-09T20:27:48.196Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/93/f28a696fa750b9b608baa236f8225dd3290e5aff27433b06143adc025961/triton-3.3.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ce4700fc14032af1e049005ae94ba908e71cd6c2df682239aed08e49bc71b742", size = 156580729, upload-time = "2025-04-09T20:27:55.424Z" },
+]
+
 [[package]]
 name = "typing-extensions"
 version = "4.13.2"