Skip to main content

ONNX Runtime GenAI

Run SLMs/LLMs and multi-modal models on-device and in the cloud with ONNX Runtime.

For more details, see: docs https://onnxruntime.ai/docs/genai and repo: https://github.com/microsoft/onnxruntime-genai

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

onnxruntime_genai_cuda-0.15.0-cp314-cp314-win_arm64.whl (8.2 MB view details)

Uploaded CPython 3.14Windows ARM64

onnxruntime_genai_cuda-0.15.0-cp314-cp314-win_amd64.whl (10.5 MB view details)

Uploaded CPython 3.14Windows x86-64

onnxruntime_genai_cuda-0.15.0-cp314-cp314-manylinux_2_28_x86_64.whl (18.2 MB view details)

Uploaded CPython 3.14manylinux: glibc 2.28+ x86-64

onnxruntime_genai_cuda-0.15.0-cp313-cp313-win_arm64.whl (8.1 MB view details)

Uploaded CPython 3.13Windows ARM64

onnxruntime_genai_cuda-0.15.0-cp313-cp313-win_amd64.whl (10.4 MB view details)

Uploaded CPython 3.13Windows x86-64

onnxruntime_genai_cuda-0.15.0-cp313-cp313-manylinux_2_28_x86_64.whl (18.2 MB view details)

Uploaded CPython 3.13manylinux: glibc 2.28+ x86-64

onnxruntime_genai_cuda-0.15.0-cp312-cp312-win_arm64.whl (8.1 MB view details)

Uploaded CPython 3.12Windows ARM64

onnxruntime_genai_cuda-0.15.0-cp312-cp312-win_amd64.whl (10.4 MB view details)

Uploaded CPython 3.12Windows x86-64

onnxruntime_genai_cuda-0.15.0-cp312-cp312-manylinux_2_28_x86_64.whl (18.2 MB view details)

Uploaded CPython 3.12manylinux: glibc 2.28+ x86-64

onnxruntime_genai_cuda-0.15.0-cp311-cp311-win_arm64.whl (8.1 MB view details)

Uploaded CPython 3.11Windows ARM64

onnxruntime_genai_cuda-0.15.0-cp311-cp311-win_amd64.whl (10.4 MB view details)

Uploaded CPython 3.11Windows x86-64

onnxruntime_genai_cuda-0.15.0-cp311-cp311-manylinux_2_28_x86_64.whl (18.2 MB view details)

Uploaded CPython 3.11manylinux: glibc 2.28+ x86-64

File details

Details for the file onnxruntime_genai_cuda-0.15.0-cp314-cp314-win_arm64.whl.

File metadata

File hashes

Hashes for onnxruntime_genai_cuda-0.15.0-cp314-cp314-win_arm64.whl
Algorithm Hash digest
SHA256 693794051758e0d275caa1b0d995dde707fc080c27fdaff25b010636813ca374
MD5 563fcd931c4901d34baa163b149e281c
BLAKE2b-256 5f67ec9a37b04867683bc2e2d2f22b40e28b3b4817998b15121ad6a2f536d146

See more details on using hashes here.

File details

Details for the file onnxruntime_genai_cuda-0.15.0-cp314-cp314-win_amd64.whl.

File metadata

File hashes

Hashes for onnxruntime_genai_cuda-0.15.0-cp314-cp314-win_amd64.whl
Algorithm Hash digest
SHA256 4b5d187d4442f5cc41f14d1922635dd422aae3f3ce9de0f43f50604350050cba
MD5 38bfe610a622d0efd05c010569594ff6
BLAKE2b-256 70e2b22055193bc81896f3bcb1e1fde99219dbcc1c204fd7c37b5ee861163c7c

See more details on using hashes here.

File details

Details for the file onnxruntime_genai_cuda-0.15.0-cp314-cp314-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for onnxruntime_genai_cuda-0.15.0-cp314-cp314-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 cc501fdca937986bd2163c52fc1792ff9186a510c02eabb85f1ae217e79c7224
MD5 220e69106bae2da51f74a8bd81c9f6b8
BLAKE2b-256 0b8893f427f5c9a2f3d7a7e004d94d302705a6832c151085cec13686d2863bdc

See more details on using hashes here.

File details

Details for the file onnxruntime_genai_cuda-0.15.0-cp313-cp313-win_arm64.whl.

File metadata

File hashes

Hashes for onnxruntime_genai_cuda-0.15.0-cp313-cp313-win_arm64.whl
Algorithm Hash digest
SHA256 95df2a06ba6e7d812af63a7e99a6803e0be279ae6391467db184b0faa3761b7c
MD5 56ecc52958057a89c5d0fb2ea7e02506
BLAKE2b-256 d58900705fe445cfdfa7a94457b7cfb477c0b7db80378b120acae51030b683b7

See more details on using hashes here.

File details

Details for the file onnxruntime_genai_cuda-0.15.0-cp313-cp313-win_amd64.whl.

File metadata

File hashes

Hashes for onnxruntime_genai_cuda-0.15.0-cp313-cp313-win_amd64.whl
Algorithm Hash digest
SHA256 a686d17686e21cdd906b32e08f85615a2c70c25c9ae0d6b0acea06f8cf61a554
MD5 e82560b331f292f28b8052b0695c70ab
BLAKE2b-256 7c8a727e04f9e074d77b6aabb5818317963eaac9190802f9aa8fa46132eb012b

See more details on using hashes here.

File details

Details for the file onnxruntime_genai_cuda-0.15.0-cp313-cp313-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for onnxruntime_genai_cuda-0.15.0-cp313-cp313-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 7296b5ea5755afc4fc6925a7f3a977beccdcbe0a01d0c996d293c5b36968678b
MD5 3ac8897e7c27eba672e504727b0eadb7
BLAKE2b-256 93b7705adf77fe85429bbef87b9143e38f8d39c84f51acebf740ac5a655fa921

See more details on using hashes here.

File details

Details for the file onnxruntime_genai_cuda-0.15.0-cp312-cp312-win_arm64.whl.

File metadata

File hashes

Hashes for onnxruntime_genai_cuda-0.15.0-cp312-cp312-win_arm64.whl
Algorithm Hash digest
SHA256 208421245112d0f707c057b7c17479e4bb335df1b99f2e82c0b5d96d5317ac97
MD5 05e3f8739d57168d51874c3e6b3e6d5c
BLAKE2b-256 90d064a45e44a64fcaa2cb25f4b4b987ac79dfc643d7f222d9859ca0ce0af580

See more details on using hashes here.

File details

Details for the file onnxruntime_genai_cuda-0.15.0-cp312-cp312-win_amd64.whl.

File metadata

File hashes

Hashes for onnxruntime_genai_cuda-0.15.0-cp312-cp312-win_amd64.whl
Algorithm Hash digest
SHA256 117b79743b32ef0de45f17b8f49ba55321b9bcb1c04d3db1c23e59ec90a6b5f8
MD5 bca367fcc6bff38dd1358162cd44f81c
BLAKE2b-256 b8cf5f337e070ad9491300f70ba4b662c9686e1d531a9772c215ec53919f88b4

See more details on using hashes here.

File details

Details for the file onnxruntime_genai_cuda-0.15.0-cp312-cp312-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for onnxruntime_genai_cuda-0.15.0-cp312-cp312-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 8e5b06a4a35138163c3129843802eace6eadc615e4178cc9dbb74cab18b9922d
MD5 3d9b25cf89b85fcf409d56502f554d81
BLAKE2b-256 e9fc910cf7d35ffa205f78d150ad657f4bfd735ce8a30fb364d6507e9c5309d3

See more details on using hashes here.

File details

Details for the file onnxruntime_genai_cuda-0.15.0-cp311-cp311-win_arm64.whl.

File metadata

File hashes

Hashes for onnxruntime_genai_cuda-0.15.0-cp311-cp311-win_arm64.whl
Algorithm Hash digest
SHA256 b2380100090ba9984b84eb604921bda8770ff3ab79bda8972dfe24d2b86a3c78
MD5 8996d5847cd59bb37bcae07c4c4e329a
BLAKE2b-256 9437f5f937e0b4a38eaebf90592592c18d3fafc391c960a5dcaf4f23515433b4

See more details on using hashes here.

File details

Details for the file onnxruntime_genai_cuda-0.15.0-cp311-cp311-win_amd64.whl.

File metadata

File hashes

Hashes for onnxruntime_genai_cuda-0.15.0-cp311-cp311-win_amd64.whl
Algorithm Hash digest
SHA256 f381d287d6c73009c3b5e058be8f1a71408b103b5955959b68de3e5f04f44027
MD5 5b2a95b9fc36a56618a0ca731a354241
BLAKE2b-256 08903caaaa8d20e927a058573e8c5f170ae2dfda4b8d7ebbc68b8f98153b09f0

See more details on using hashes here.

File details

Details for the file onnxruntime_genai_cuda-0.15.0-cp311-cp311-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for onnxruntime_genai_cuda-0.15.0-cp311-cp311-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 8ec2aaafe846d736cb35bb591bf1c7541d73e9ce2e4cb3290c942f8fafa80713
MD5 b48d8e85c23f2d8e5a0c90a02a3f94ce
BLAKE2b-256 f3867cadad32c3a2a1529a2854856c5699d0ec9d548cde87c3134a44ae184dea

See more details on using hashes here.

Release history Release notifications | RSS feed

0.15.2

12 files

0.15.1

12 files

This release

0.15.0 This release

12 files

0.14.1

8 files

0.14.0

8 files

0.13.2

8 files

0.13.1

8 files

0.13.0

8 files

0.12.2

8 files

0.12.1

8 files

0.12.0

8 files

0.11.4

8 files

0.11.3

8 files

0.11.2

8 files

0.11.1

8 files

0.11.0

8 files

0.10.0

8 files

0.9.2

8 files

0.9.1

8 files

0.9.0

8 files

0.8.3

8 files

0.8.2

8 files

0.8.1

8 files

0.8.0

8 files

0.7.1

8 files

0.7.0

8 files

0.6.0

8 files

0.5.2

6 files

0.5.1

6 files

0.5.0

6 files

0.4.0

10 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page