From f728a1a975324fa2daf4dfdd4213635df96072b8 Mon Sep 17 00:00:00 2001 From: Adil Hafeez Date: Fri, 11 Jul 2025 23:09:18 -0700 Subject: [PATCH] update torch==2.6.0 --- .github/workflows/e2e_archgw.yml | 2 +- .../workflows/e2e_test_currency_convert.yml | 2 +- .../e2e_test_preference_based_routing.yml | 2 +- .github/workflows/validate_arch_config.yml | 2 +- README.md | 2 +- arch/tools/README.md | 2 +- arch/tools/cli/consts.py | 2 +- arch/tools/poetry.lock | 4 +- arch/tools/pyproject.toml | 4 +- .../preference_based_routing/README.md | 4 +- docs/source/conf.py | 2 +- docs/source/get_started/quickstart.rst | 2 +- model_server/poetry.lock | 192 ++++++++++-------- model_server/pyproject.toml | 4 +- 14 files changed, 124 insertions(+), 102 deletions(-) diff --git a/.github/workflows/e2e_archgw.yml b/.github/workflows/e2e_archgw.yml index 9f0f1061..633a32d8 100644 --- a/.github/workflows/e2e_archgw.yml +++ b/.github/workflows/e2e_archgw.yml @@ -24,7 +24,7 @@ jobs: - name: build arch docker image run: | - cd ../../ && docker build -f arch/Dockerfile . -t katanemo/archgw -t katanemo/archgw:0.3.4 -t katanemo/archgw:latest + cd ../../ && docker build -f arch/Dockerfile . -t katanemo/archgw -t katanemo/archgw:0.3.5 -t katanemo/archgw:latest - name: start archgw env: diff --git a/.github/workflows/e2e_test_currency_convert.yml b/.github/workflows/e2e_test_currency_convert.yml index 6a80760b..de29ed72 100644 --- a/.github/workflows/e2e_test_currency_convert.yml +++ b/.github/workflows/e2e_test_currency_convert.yml @@ -24,7 +24,7 @@ jobs: - name: build arch docker image run: | - docker build -f arch/Dockerfile . -t katanemo/archgw -t katanemo/archgw:0.3.4 + docker build -f arch/Dockerfile . -t katanemo/archgw -t katanemo/archgw:0.3.5 - name: install poetry run: | diff --git a/.github/workflows/e2e_test_preference_based_routing.yml b/.github/workflows/e2e_test_preference_based_routing.yml index e9564882..c1ab7050 100644 --- a/.github/workflows/e2e_test_preference_based_routing.yml +++ b/.github/workflows/e2e_test_preference_based_routing.yml @@ -24,7 +24,7 @@ jobs: - name: build arch docker image run: | - docker build -f arch/Dockerfile . -t katanemo/archgw -t katanemo/archgw:0.3.4 + docker build -f arch/Dockerfile . -t katanemo/archgw -t katanemo/archgw:0.3.5 - name: install poetry run: | diff --git a/.github/workflows/validate_arch_config.yml b/.github/workflows/validate_arch_config.yml index e5fd6acb..c3dbfeb3 100644 --- a/.github/workflows/validate_arch_config.yml +++ b/.github/workflows/validate_arch_config.yml @@ -24,7 +24,7 @@ jobs: - name: build arch docker image run: | - docker build -f arch/Dockerfile . -t katanemo/archgw -t katanemo/archgw:0.3.4 + docker build -f arch/Dockerfile . -t katanemo/archgw -t katanemo/archgw:0.3.5 - name: validate arch config run: | diff --git a/README.md b/README.md index 136d48fc..d71cf1b4 100644 --- a/README.md +++ b/README.md @@ -82,7 +82,7 @@ Arch's CLI allows you to manage and interact with the Arch gateway efficiently. ```console $ python -m venv venv $ source venv/bin/activate # On Windows, use: venv\Scripts\activate -$ pip install archgw==0.3.4 +$ pip install archgw==0.3.5 ``` ### Build Agentic Apps with Arch Gateway diff --git a/arch/tools/README.md b/arch/tools/README.md index 7d098186..e4e45284 100644 --- a/arch/tools/README.md +++ b/arch/tools/README.md @@ -19,7 +19,7 @@ source venv/bin/activate ### Step 3: Run the build script ```bash -pip install archgw==0.3.4 +pip install archgw==0.3.5 ``` ## Uninstall Instructions: archgw CLI diff --git a/arch/tools/cli/consts.py b/arch/tools/cli/consts.py index d0307211..9114f53f 100644 --- a/arch/tools/cli/consts.py +++ b/arch/tools/cli/consts.py @@ -10,4 +10,4 @@ SERVICE_NAME_MODEL_SERVER = "model_server" SERVICE_ALL = "all" MODEL_SERVER_LOG_FILE = "~/archgw_logs/modelserver.log" ARCHGW_DOCKER_NAME = "archgw" -ARCHGW_DOCKER_IMAGE = os.getenv("ARCHGW_DOCKER_IMAGE", "katanemo/archgw:0.3.4") +ARCHGW_DOCKER_IMAGE = os.getenv("ARCHGW_DOCKER_IMAGE", "katanemo/archgw:0.3.5") diff --git a/arch/tools/poetry.lock b/arch/tools/poetry.lock index d66eae75..4491dd1f 100644 --- a/arch/tools/poetry.lock +++ b/arch/tools/poetry.lock @@ -2,7 +2,7 @@ [[package]] name = "archgw_modelserver" -version = "0.3.4" +version = "0.3.5" description = "A model server for serving models" optional = false python-versions = "*" @@ -576,4 +576,4 @@ files = [ [metadata] lock-version = "2.0" python-versions = "^3.10" -content-hash = "d1e256d1bb05fab98731edc11ea15391e9611acf2c3461d00d25c5fa0040de23" +content-hash = "e86085ff732244cb68d2e3f7f4c2903f4a8a50cc7e0963324c2506f0de90df11" diff --git a/arch/tools/pyproject.toml b/arch/tools/pyproject.toml index 179c36d5..cf75165c 100644 --- a/arch/tools/pyproject.toml +++ b/arch/tools/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "archgw" -version = "0.3.4" +version = "0.3.5" description = "Python-based CLI tool to manage Arch Gateway." authors = ["Katanemo Labs, Inc."] packages = [ @@ -10,7 +10,7 @@ readme = "README.md" [tool.poetry.dependencies] python = "^3.10" -archgw_modelserver = "^0.3.4" +archgw_modelserver = "^0.3.5" click = "^8.1.7" jinja2 = "^3.1.4" jsonschema = "^4.23.0" diff --git a/demos/use_cases/preference_based_routing/README.md b/demos/use_cases/preference_based_routing/README.md index 4031069d..7b988bcc 100644 --- a/demos/use_cases/preference_based_routing/README.md +++ b/demos/use_cases/preference_based_routing/README.md @@ -14,9 +14,9 @@ Make sure your machine is up to date with [latest version of archgw]([url](https 2. start archgw in the foreground ```bash (venv) $ archgw up --service archgw --foreground -2025-05-30 18:00:09,953 - cli.main - INFO - Starting archgw cli version: 0.3.4 +2025-05-30 18:00:09,953 - cli.main - INFO - Starting archgw cli version: 0.3.5 2025-05-30 18:00:09,953 - cli.main - INFO - Validating /Users/adilhafeez/src/intelligent-prompt-gateway/demos/use_cases/preference_based_routing/arch_config.yaml -2025-05-30 18:00:10,422 - cli.core - INFO - Starting arch gateway, image name: archgw, tag: katanemo/archgw:0.3.4 +2025-05-30 18:00:10,422 - cli.core - INFO - Starting arch gateway, image name: archgw, tag: katanemo/archgw:0.3.5 2025-05-30 18:00:10,662 - cli.core - INFO - archgw status: running, health status: starting 2025-05-30 18:00:11,712 - cli.core - INFO - archgw status: running, health status: starting 2025-05-30 18:00:12,761 - cli.core - INFO - archgw is running and is healthy! diff --git a/docs/source/conf.py b/docs/source/conf.py index 4790156e..1f78ac50 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -15,7 +15,7 @@ from sphinxawesome_theme.postprocess import Icons project = "Arch Docs" copyright = "2025, Katanemo Labs, Inc" author = "Katanemo Labs, Inc" -release = " v0.3.4" +release = " v0.3.5" # -- General configuration --------------------------------------------------- # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration diff --git a/docs/source/get_started/quickstart.rst b/docs/source/get_started/quickstart.rst index bec37d90..67337e5b 100644 --- a/docs/source/get_started/quickstart.rst +++ b/docs/source/get_started/quickstart.rst @@ -25,7 +25,7 @@ Arch's CLI allows you to manage and interact with the Arch gateway efficiently. $ python -m venv venv $ source venv/bin/activate # On Windows, use: venv\Scripts\activate - $ pip install archgw==0.3.4 + $ pip install archgw==0.3.5 Build AI Agent with Arch Gateway diff --git a/model_server/poetry.lock b/model_server/poetry.lock index 2debff66..84709b36 100644 --- a/model_server/poetry.lock +++ b/model_server/poetry.lock @@ -879,46 +879,50 @@ files = [ [[package]] name = "nvidia-cublas-cu12" -version = "12.1.3.1" +version = "12.4.5.8" description = "CUBLAS native runtime libraries" optional = false python-versions = ">=3" files = [ - {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl", hash = "sha256:ee53ccca76a6fc08fb9701aa95b6ceb242cdaab118c3bb152af4e579af792728"}, - {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-win_amd64.whl", hash = "sha256:2b964d60e8cf11b5e1073d179d85fa340c120e99b3067558f3cf98dd69d02906"}, + {file = "nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_aarch64.whl", hash = "sha256:0f8aa1706812e00b9f19dfe0cdb3999b092ccb8ca168c0db5b8ea712456fd9b3"}, + {file = "nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl", hash = "sha256:2fc8da60df463fdefa81e323eef2e36489e1c94335b5358bcb38360adf75ac9b"}, + {file = "nvidia_cublas_cu12-12.4.5.8-py3-none-win_amd64.whl", hash = "sha256:5a796786da89203a0657eda402bcdcec6180254a8ac22d72213abc42069522dc"}, ] [[package]] name = "nvidia-cuda-cupti-cu12" -version = "12.1.105" +version = "12.4.127" description = "CUDA profiling tools runtime libs." optional = false python-versions = ">=3" files = [ - {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:e54fde3983165c624cb79254ae9818a456eb6e87a7fd4d56a2352c24ee542d7e"}, - {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:bea8236d13a0ac7190bd2919c3e8e6ce1e402104276e6f9694479e48bb0eb2a4"}, + {file = "nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:79279b35cf6f91da114182a5ce1864997fd52294a87a16179ce275773799458a"}, + {file = "nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:9dec60f5ac126f7bb551c055072b69d85392b13311fcc1bcda2202d172df30fb"}, + {file = "nvidia_cuda_cupti_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:5688d203301ab051449a2b1cb6690fbe90d2b372f411521c86018b950f3d7922"}, ] [[package]] name = "nvidia-cuda-nvrtc-cu12" -version = "12.1.105" +version = "12.4.127" description = "NVRTC native runtime libraries" optional = false python-versions = ">=3" files = [ - {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:339b385f50c309763ca65456ec75e17bbefcbbf2893f462cb8b90584cd27a1c2"}, - {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:0a98a522d9ff138b96c010a65e145dc1b4850e9ecb75a0172371793752fd46ed"}, + {file = "nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:0eedf14185e04b76aa05b1fea04133e59f465b6f960c0cbf4e37c3cb6b0ea198"}, + {file = "nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:a178759ebb095827bd30ef56598ec182b85547f1508941a3d560eb7ea1fbf338"}, + {file = "nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:a961b2f1d5f17b14867c619ceb99ef6fcec12e46612711bcec78eb05068a60ec"}, ] [[package]] name = "nvidia-cuda-runtime-cu12" -version = "12.1.105" +version = "12.4.127" description = "CUDA Runtime native Libraries" optional = false python-versions = ">=3" files = [ - {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:6e258468ddf5796e25f1dc591a31029fa317d97a0a94ed93468fc86301d61e40"}, - {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:dfb46ef84d73fababab44cf03e3b83f80700d27ca300e537f85f636fac474344"}, + {file = "nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:961fe0e2e716a2a1d967aab7caee97512f71767f852f67432d572e36cb3a11f3"}, + {file = "nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:64403288fa2136ee8e467cdc9c9427e0434110899d07c779f25b5c068934faa5"}, + {file = "nvidia_cuda_runtime_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:09c2e35f48359752dfa822c09918211844a3d93c100a715d79b59591130c5e1e"}, ] [[package]] @@ -937,35 +941,41 @@ nvidia-cublas-cu12 = "*" [[package]] name = "nvidia-cufft-cu12" -version = "11.0.2.54" +version = "11.2.1.3" description = "CUFFT native runtime libraries" optional = false python-versions = ">=3" files = [ - {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl", hash = "sha256:794e3948a1aa71fd817c3775866943936774d1c14e7628c74f6f7417224cdf56"}, - {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-win_amd64.whl", hash = "sha256:d9ac353f78ff89951da4af698f80870b1534ed69993f10a4cf1d96f21357e253"}, + {file = "nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_aarch64.whl", hash = "sha256:5dad8008fc7f92f5ddfa2101430917ce2ffacd86824914c82e28990ad7f00399"}, + {file = "nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl", hash = "sha256:f083fc24912aa410be21fa16d157fed2055dab1cc4b6934a0e03cba69eb242b9"}, + {file = "nvidia_cufft_cu12-11.2.1.3-py3-none-win_amd64.whl", hash = "sha256:d802f4954291101186078ccbe22fc285a902136f974d369540fd4a5333d1440b"}, ] +[package.dependencies] +nvidia-nvjitlink-cu12 = "*" + [[package]] name = "nvidia-curand-cu12" -version = "10.3.2.106" +version = "10.3.5.147" description = "CURAND native runtime libraries" optional = false python-versions = ">=3" files = [ - {file = "nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:9d264c5036dde4e64f1de8c50ae753237c12e0b1348738169cd0f8a536c0e1e0"}, - {file = "nvidia_curand_cu12-10.3.2.106-py3-none-win_amd64.whl", hash = "sha256:75b6b0c574c0037839121317e17fd01f8a69fd2ef8e25853d826fec30bdba74a"}, + {file = "nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1f173f09e3e3c76ab084aba0de819c49e56614feae5c12f69883f4ae9bb5fad9"}, + {file = "nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl", hash = "sha256:a88f583d4e0bb643c49743469964103aa59f7f708d862c3ddb0fc07f851e3b8b"}, + {file = "nvidia_curand_cu12-10.3.5.147-py3-none-win_amd64.whl", hash = "sha256:f307cc191f96efe9e8f05a87096abc20d08845a841889ef78cb06924437f6771"}, ] [[package]] name = "nvidia-cusolver-cu12" -version = "11.4.5.107" +version = "11.6.1.9" description = "CUDA solver native runtime libraries" optional = false python-versions = ">=3" files = [ - {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd"}, - {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-win_amd64.whl", hash = "sha256:74e0c3a24c78612192a74fcd90dd117f1cf21dea4822e66d89e8ea80e3cd2da5"}, + {file = "nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_aarch64.whl", hash = "sha256:d338f155f174f90724bbde3758b7ac375a70ce8e706d70b018dd3375545fc84e"}, + {file = "nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl", hash = "sha256:19e33fa442bcfd085b3086c4ebf7e8debc07cfe01e11513cc6d332fd918ac260"}, + {file = "nvidia_cusolver_cu12-11.6.1.9-py3-none-win_amd64.whl", hash = "sha256:e77314c9d7b694fcebc84f58989f3aa4fb4cb442f12ca1a9bde50f5e8f6d1b9c"}, ] [package.dependencies] @@ -975,50 +985,63 @@ nvidia-nvjitlink-cu12 = "*" [[package]] name = "nvidia-cusparse-cu12" -version = "12.1.0.106" +version = "12.3.1.170" description = "CUSPARSE native runtime libraries" optional = false python-versions = ">=3" files = [ - {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c"}, - {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-win_amd64.whl", hash = "sha256:b798237e81b9719373e8fae8d4f091b70a0cf09d9d85c95a557e11df2d8e9a5a"}, + {file = "nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_aarch64.whl", hash = "sha256:9d32f62896231ebe0480efd8a7f702e143c98cfaa0e8a76df3386c1ba2b54df3"}, + {file = "nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl", hash = "sha256:ea4f11a2904e2a8dc4b1833cc1b5181cde564edd0d5cd33e3c168eff2d1863f1"}, + {file = "nvidia_cusparse_cu12-12.3.1.170-py3-none-win_amd64.whl", hash = "sha256:9bc90fb087bc7b4c15641521f31c0371e9a612fc2ba12c338d3ae032e6b6797f"}, ] [package.dependencies] nvidia-nvjitlink-cu12 = "*" +[[package]] +name = "nvidia-cusparselt-cu12" +version = "0.6.2" +description = "NVIDIA cuSPARSELt" +optional = false +python-versions = "*" +files = [ + {file = "nvidia_cusparselt_cu12-0.6.2-py3-none-manylinux2014_aarch64.whl", hash = "sha256:067a7f6d03ea0d4841c85f0c6f1991c5dda98211f6302cb83a4ab234ee95bef8"}, + {file = "nvidia_cusparselt_cu12-0.6.2-py3-none-manylinux2014_x86_64.whl", hash = "sha256:df2c24502fd76ebafe7457dbc4716b2fec071aabaed4fb7691a201cde03704d9"}, + {file = "nvidia_cusparselt_cu12-0.6.2-py3-none-win_amd64.whl", hash = "sha256:0057c91d230703924c0422feabe4ce768841f9b4b44d28586b6f6d2eb86fbe70"}, +] + [[package]] name = "nvidia-nccl-cu12" -version = "2.20.5" +version = "2.21.5" description = "NVIDIA Collective Communication Library (NCCL) Runtime" optional = false python-versions = ">=3" files = [ - {file = "nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1fc150d5c3250b170b29410ba682384b14581db722b2531b0d8d33c595f33d01"}, - {file = "nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:057f6bf9685f75215d0c53bf3ac4a10b3e6578351de307abad9e18a99182af56"}, + {file = "nvidia_nccl_cu12-2.21.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:8579076d30a8c24988834445f8d633c697d42397e92ffc3f63fa26766d25e0a0"}, ] [[package]] name = "nvidia-nvjitlink-cu12" -version = "12.9.86" +version = "12.4.127" description = "Nvidia JIT LTO Library" optional = false python-versions = ">=3" files = [ - {file = "nvidia_nvjitlink_cu12-12.9.86-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:e3f1171dbdc83c5932a45f0f4c99180a70de9bd2718c1ab77d14104f6d7147f9"}, - {file = "nvidia_nvjitlink_cu12-12.9.86-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:994a05ef08ef4b0b299829cde613a424382aff7efb08a7172c1fa616cc3af2ca"}, - {file = "nvidia_nvjitlink_cu12-12.9.86-py3-none-win_amd64.whl", hash = "sha256:cc6fcec260ca843c10e34c936921a1c426b351753587fdd638e8cff7b16bb9db"}, + {file = "nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:4abe7fef64914ccfa909bc2ba39739670ecc9e820c83ccc7a6ed414122599b83"}, + {file = "nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:06b3b9b25bf3f8af351d664978ca26a16d2c5127dbd53c0497e28d1fb9611d57"}, + {file = "nvidia_nvjitlink_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:fd9020c501d27d135f983c6d3e244b197a7ccad769e34df53a42e276b0e25fa1"}, ] [[package]] name = "nvidia-nvtx-cu12" -version = "12.1.105" +version = "12.4.127" description = "NVIDIA Tools Extension" optional = false python-versions = ">=3" files = [ - {file = "nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:dc21cf308ca5691e7c04d962e213f8a4aa9bbfa23d95412f452254c2caeb09e5"}, - {file = "nvidia_nvtx_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:65f4d98982b31b60026e0e6de73fbdfc09d08a96f4656dd3665ca616a11e1e82"}, + {file = "nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:7959ad635db13edf4fc65c06a6e9f9e55fc2f92596db928d169c0bb031e88ef3"}, + {file = "nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:781e950d9b9f60d8241ccea575b32f5105a5baf4c2351cab5256a24869f12a1a"}, + {file = "nvidia_nvtx_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:641dccaaa1139f3ffb0d3164b4b84f9d253397e38246a4f2f36728b48566d485"}, ] [[package]] @@ -1854,13 +1877,13 @@ full = ["httpx (>=0.22.0)", "itsdangerous", "jinja2", "python-multipart (>=0.0.7 [[package]] name = "sympy" -version = "1.14.0" +version = "1.13.1" description = "Computer algebra system (CAS) in Python" optional = false -python-versions = ">=3.9" +python-versions = ">=3.8" files = [ - {file = "sympy-1.14.0-py3-none-any.whl", hash = "sha256:e091cc3e99d2141a0ba2847328f5479b05d94a6635cb96148ccb3f34671bd8f5"}, - {file = "sympy-1.14.0.tar.gz", hash = "sha256:d3d3fe8df1e5a0b42f0e7bdf50541697dbe7d23746e894990c030e2b05e72517"}, + {file = "sympy-1.13.1-py3-none-any.whl", hash = "sha256:db36cdc64bf61b9b24578b6f7bab1ecdd2452cf008f34faa33776680c26d66f8"}, + {file = "sympy-1.13.1.tar.gz", hash = "sha256:9cebf7e04ff162015ce31c9c6c9144daa34a93bd082f54fd8f12deca4f47515f"}, ] [package.dependencies] @@ -1944,31 +1967,31 @@ files = [ [[package]] name = "torch" -version = "2.4.1" +version = "2.6.0" description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration" optional = false -python-versions = ">=3.8.0" +python-versions = ">=3.9.0" files = [ - {file = "torch-2.4.1-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:362f82e23a4cd46341daabb76fba08f04cd646df9bfaf5da50af97cb60ca4971"}, - {file = "torch-2.4.1-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:e8ac1985c3ff0f60d85b991954cfc2cc25f79c84545aead422763148ed2759e3"}, - {file = "torch-2.4.1-cp310-cp310-win_amd64.whl", hash = "sha256:91e326e2ccfb1496e3bee58f70ef605aeb27bd26be07ba64f37dcaac3d070ada"}, - {file = "torch-2.4.1-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:d36a8ef100f5bff3e9c3cea934b9e0d7ea277cb8210c7152d34a9a6c5830eadd"}, - {file = "torch-2.4.1-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:0b5f88afdfa05a335d80351e3cea57d38e578c8689f751d35e0ff36bce872113"}, - {file = "torch-2.4.1-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:ef503165f2341942bfdf2bd520152f19540d0c0e34961232f134dc59ad435be8"}, - {file = "torch-2.4.1-cp311-cp311-win_amd64.whl", hash = "sha256:092e7c2280c860eff762ac08c4bdcd53d701677851670695e0c22d6d345b269c"}, - {file = "torch-2.4.1-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:ddddbd8b066e743934a4200b3d54267a46db02106876d21cf31f7da7a96f98ea"}, - {file = "torch-2.4.1-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:fdc4fe11db3eb93c1115d3e973a27ac7c1a8318af8934ffa36b0370efe28e042"}, - {file = "torch-2.4.1-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:18835374f599207a9e82c262153c20ddf42ea49bc76b6eadad8e5f49729f6e4d"}, - {file = "torch-2.4.1-cp312-cp312-win_amd64.whl", hash = "sha256:ebea70ff30544fc021d441ce6b219a88b67524f01170b1c538d7d3ebb5e7f56c"}, - {file = "torch-2.4.1-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:72b484d5b6cec1a735bf3fa5a1c4883d01748698c5e9cfdbeb4ffab7c7987e0d"}, - {file = "torch-2.4.1-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:c99e1db4bf0c5347107845d715b4aa1097e601bdc36343d758963055e9599d93"}, - {file = "torch-2.4.1-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:b57f07e92858db78c5b72857b4f0b33a65b00dc5d68e7948a8494b0314efb880"}, - {file = "torch-2.4.1-cp38-cp38-win_amd64.whl", hash = "sha256:f18197f3f7c15cde2115892b64f17c80dbf01ed72b008020e7da339902742cf6"}, - {file = "torch-2.4.1-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:5fc1d4d7ed265ef853579caf272686d1ed87cebdcd04f2a498f800ffc53dab71"}, - {file = "torch-2.4.1-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:40f6d3fe3bae74efcf08cb7f8295eaddd8a838ce89e9d26929d4edd6d5e4329d"}, - {file = "torch-2.4.1-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:c9299c16c9743001ecef515536ac45900247f4338ecdf70746f2461f9e4831db"}, - {file = "torch-2.4.1-cp39-cp39-win_amd64.whl", hash = "sha256:6bce130f2cd2d52ba4e2c6ada461808de7e5eccbac692525337cfb4c19421846"}, - {file = "torch-2.4.1-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:a38de2803ee6050309aac032676536c3d3b6a9804248537e38e098d0e14817ec"}, + {file = "torch-2.6.0-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:6860df13d9911ac158f4c44031609700e1eba07916fff62e21e6ffa0a9e01961"}, + {file = "torch-2.6.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:c4f103a49830ce4c7561ef4434cc7926e5a5fe4e5eb100c19ab36ea1e2b634ab"}, + {file = "torch-2.6.0-cp310-cp310-win_amd64.whl", hash = "sha256:56eeaf2ecac90da5d9e35f7f35eb286da82673ec3c582e310a8d1631a1c02341"}, + {file = "torch-2.6.0-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:09e06f9949e1a0518c5b09fe95295bc9661f219d9ecb6f9893e5123e10696628"}, + {file = "torch-2.6.0-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:7979834102cd5b7a43cc64e87f2f3b14bd0e1458f06e9f88ffa386d07c7446e1"}, + {file = "torch-2.6.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:ccbd0320411fe1a3b3fec7b4d3185aa7d0c52adac94480ab024b5c8f74a0bf1d"}, + {file = "torch-2.6.0-cp311-cp311-win_amd64.whl", hash = "sha256:46763dcb051180ce1ed23d1891d9b1598e07d051ce4c9d14307029809c4d64f7"}, + {file = "torch-2.6.0-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:94fc63b3b4bedd327af588696559f68c264440e2503cc9e6954019473d74ae21"}, + {file = "torch-2.6.0-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:2bb8987f3bb1ef2675897034402373ddfc8f5ef0e156e2d8cfc47cacafdda4a9"}, + {file = "torch-2.6.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:b789069020c5588c70d5c2158ac0aa23fd24a028f34a8b4fcb8fcb4d7efcf5fb"}, + {file = "torch-2.6.0-cp312-cp312-win_amd64.whl", hash = "sha256:7e1448426d0ba3620408218b50aa6ada88aeae34f7a239ba5431f6c8774b1239"}, + {file = "torch-2.6.0-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:9a610afe216a85a8b9bc9f8365ed561535c93e804c2a317ef7fabcc5deda0989"}, + {file = "torch-2.6.0-cp313-cp313-manylinux1_x86_64.whl", hash = "sha256:4874a73507a300a5d089ceaff616a569e7bb7c613c56f37f63ec3ffac65259cf"}, + {file = "torch-2.6.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:a0d5e1b9874c1a6c25556840ab8920569a7a4137afa8a63a32cee0bc7d89bd4b"}, + {file = "torch-2.6.0-cp313-cp313-win_amd64.whl", hash = "sha256:510c73251bee9ba02ae1cb6c9d4ee0907b3ce6020e62784e2d7598e0cfa4d6cc"}, + {file = "torch-2.6.0-cp313-none-macosx_11_0_arm64.whl", hash = "sha256:ff96f4038f8af9f7ec4231710ed4549da1bdebad95923953a25045dcf6fd87e2"}, + {file = "torch-2.6.0-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:9ea955317cfcd3852b1402b62af258ce735c2edeee42ca9419b6bc889e5ae053"}, + {file = "torch-2.6.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:bb2c6c3e65049f081940f5ab15c9136c7de40d3f01192541c920a07c7c585b7e"}, + {file = "torch-2.6.0-cp39-cp39-win_amd64.whl", hash = "sha256:683410f97984103148e31b38a8631acf31c3034c020c0f4d26171e7626d8317a"}, + {file = "torch-2.6.0-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:265f70de5fd45b864d924b64be1797f86e76c8e48a02c2a3a6fc7ec247d2226c"}, ] [package.dependencies] @@ -1976,25 +1999,27 @@ filelock = "*" fsspec = "*" jinja2 = "*" networkx = "*" -nvidia-cublas-cu12 = {version = "12.1.3.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} -nvidia-cuda-cupti-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} -nvidia-cuda-nvrtc-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} -nvidia-cuda-runtime-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cublas-cu12 = {version = "12.4.5.8", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cuda-cupti-cu12 = {version = "12.4.127", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cuda-nvrtc-cu12 = {version = "12.4.127", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cuda-runtime-cu12 = {version = "12.4.127", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-cudnn-cu12 = {version = "9.1.0.70", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} -nvidia-cufft-cu12 = {version = "11.0.2.54", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} -nvidia-curand-cu12 = {version = "10.3.2.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} -nvidia-cusolver-cu12 = {version = "11.4.5.107", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} -nvidia-cusparse-cu12 = {version = "12.1.0.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} -nvidia-nccl-cu12 = {version = "2.20.5", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} -nvidia-nvtx-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} -setuptools = "*" -sympy = "*" -triton = {version = "3.0.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version < \"3.13\""} -typing-extensions = ">=4.8.0" +nvidia-cufft-cu12 = {version = "11.2.1.3", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-curand-cu12 = {version = "10.3.5.147", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cusolver-cu12 = {version = "11.6.1.9", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cusparse-cu12 = {version = "12.3.1.170", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cusparselt-cu12 = {version = "0.6.2", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-nccl-cu12 = {version = "2.21.5", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-nvjitlink-cu12 = {version = "12.4.127", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-nvtx-cu12 = {version = "12.4.127", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +setuptools = {version = "*", markers = "python_version >= \"3.12\""} +sympy = {version = "1.13.1", markers = "python_version >= \"3.9\""} +triton = {version = "3.2.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +typing-extensions = ">=4.10.0" [package.extras] opt-einsum = ["opt-einsum (>=3.3)"] -optree = ["optree (>=0.11.0)"] +optree = ["optree (>=0.13.0)"] [[package]] name = "tqdm" @@ -2091,21 +2116,18 @@ vision = ["Pillow (>=10.0.1,<=15.0)"] [[package]] name = "triton" -version = "3.0.0" +version = "3.2.0" description = "A language and compiler for custom Deep Learning operations" optional = false python-versions = "*" files = [ - {file = "triton-3.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e1efef76935b2febc365bfadf74bcb65a6f959a9872e5bddf44cc9e0adce1e1a"}, - {file = "triton-3.0.0-1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:5ce8520437c602fb633f1324cc3871c47bee3b67acf9756c1a66309b60e3216c"}, - {file = "triton-3.0.0-1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:34e509deb77f1c067d8640725ef00c5cbfcb2052a1a3cb6a6d343841f92624eb"}, - {file = "triton-3.0.0-1-cp38-cp38-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:bcbf3b1c48af6a28011a5c40a5b3b9b5330530c3827716b5fbf6d7adcc1e53e9"}, - {file = "triton-3.0.0-1-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:6e5727202f7078c56f91ff13ad0c1abab14a0e7f2c87e91b12b6f64f3e8ae609"}, + {file = "triton-3.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b3e54983cd51875855da7c68ec05c05cf8bb08df361b1d5b69e05e40b0c9bd62"}, + {file = "triton-3.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8009a1fb093ee8546495e96731336a33fb8856a38e45bb4ab6affd6dbc3ba220"}, + {file = "triton-3.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8d9b215efc1c26fa7eefb9a157915c92d52e000d2bf83e5f69704047e63f125c"}, + {file = "triton-3.2.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e5dfa23ba84541d7c0a531dfce76d8bcd19159d50a4a8b14ad01e91734a5c1b0"}, + {file = "triton-3.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:30ceed0eff2c4a73b14eb63e052992f44bbdf175f3fad21e1ac8097a772de7ee"}, ] -[package.dependencies] -filelock = "*" - [package.extras] build = ["cmake (>=3.20)", "lit"] tests = ["autopep8", "flake8", "isort", "llnl-hatchet", "numpy", "pytest", "scipy (>=1.7.1)"] @@ -2327,4 +2349,4 @@ type = ["pytest-mypy"] [metadata] lock-version = "2.0" python-versions = "^3.10" -content-hash = "88cf76348bd82068cfc2e48d082ac09c9ae50c829f6c9bcb6e07b879214d6f0d" +content-hash = "ebac68ba32e594c1b83c8a5986e32b5d6634eb0b0e60937dec37e6b90ea6a63d" diff --git a/model_server/pyproject.toml b/model_server/pyproject.toml index 76807337..cabb4a43 100644 --- a/model_server/pyproject.toml +++ b/model_server/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "archgw_modelserver" -version = "0.3.4" +version = "0.3.5" description = "A model server for serving models" authors = ["Katanemo Labs, Inc "] license = "Apache 2.0" @@ -12,7 +12,7 @@ packages = [ [tool.poetry.dependencies] python = "^3.10" fastapi = "0.115.0" -torch = "2.4.1" +torch = "2.6.0" uvicorn = "0.31.0" transformers = "^4.37.0" accelerate = "^1.0.0"