# ONNX Runtime generate() API
Run SLMs/LLMs and multi modal models on-device and in the cloud with ONNX Runtime.
Model architectures supported so far (and more coming soon): Gemma, Llama, Mistral, Phi (language and vision).
For more details, see: docs https://onnxruntime.ai/docs/genai and repo: https://github.com/microsoft/onnxruntime-genai
Raw data
{
"_id": null,
"home_page": null,
"name": "onnxruntime-genai-cuda",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": null,
"author": "Microsoft Corporation",
"author_email": "onnxruntime-genai@microsoft.com",
"download_url": null,
"platform": null,
"description": "# ONNX Runtime generate() API\n\nRun SLMs/LLMs and multi modal models on-device and in the cloud with ONNX Runtime.\n\nModel architectures supported so far (and more coming soon): Gemma, Llama, Mistral, Phi (language and vision).\n\nFor more details, see: docs https://onnxruntime.ai/docs/genai and repo: https://github.com/microsoft/onnxruntime-genai\n",
"bugtrack_url": null,
"license": "MIT License",
"summary": "ONNX Runtime generate() API",
"version": "0.5.1",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "7a44c3ef5ec3085184f538c68c63a0ac84bd3f2ce5f097d45588d91e16c2fe89",
"md5": "a987595e2bb50ce7cc94258aad3a91e9",
"sha256": "ae9974ed09a93c051ff87811b39998eb473ed21b9020d740dc4fd5f3ed2625f9"
},
"downloads": -1,
"filename": "onnxruntime_genai_cuda-0.5.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl",
"has_sig": false,
"md5_digest": "a987595e2bb50ce7cc94258aad3a91e9",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 15061624,
"upload_time": "2024-11-13T19:33:38",
"upload_time_iso_8601": "2024-11-13T19:33:38.751482Z",
"url": "https://files.pythonhosted.org/packages/7a/44/c3ef5ec3085184f538c68c63a0ac84bd3f2ce5f097d45588d91e16c2fe89/onnxruntime_genai_cuda-0.5.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "d5795035356ed5dc677438842ff47097ae170997c5e2677926d1bc40e56598bc",
"md5": "0a97de66fbae89ec11c9c7809ac2a5d2",
"sha256": "e1b7a5c8fc7fbd22fb9812731d2ba8f8855482d3e9b0ea21cfc2d099526ddc75"
},
"downloads": -1,
"filename": "onnxruntime_genai_cuda-0.5.1-cp310-cp310-win_amd64.whl",
"has_sig": false,
"md5_digest": "0a97de66fbae89ec11c9c7809ac2a5d2",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 14365196,
"upload_time": "2024-11-13T19:34:05",
"upload_time_iso_8601": "2024-11-13T19:34:05.297348Z",
"url": "https://files.pythonhosted.org/packages/d5/79/5035356ed5dc677438842ff47097ae170997c5e2677926d1bc40e56598bc/onnxruntime_genai_cuda-0.5.1-cp310-cp310-win_amd64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "830382d59cdea80847ddc93bd4c5c13a0280cc9334d0f9b860f7a9806af2bb2f",
"md5": "3588d139d8b8fb3bfca9db37d6c9b4d7",
"sha256": "03e108bc03e57e033523e4bc0ddaf6df340084a708bf490f25748c1fc4888c2f"
},
"downloads": -1,
"filename": "onnxruntime_genai_cuda-0.5.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl",
"has_sig": false,
"md5_digest": "3588d139d8b8fb3bfca9db37d6c9b4d7",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 15061693,
"upload_time": "2024-11-13T19:33:41",
"upload_time_iso_8601": "2024-11-13T19:33:41.965918Z",
"url": "https://files.pythonhosted.org/packages/83/03/82d59cdea80847ddc93bd4c5c13a0280cc9334d0f9b860f7a9806af2bb2f/onnxruntime_genai_cuda-0.5.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "fdc642a19bc84117984a1a4c8bee0fc61e75ff972de1606a9d70d55041fbbf82",
"md5": "52beb375bfceacb78a5dabefdb24c453",
"sha256": "bb7bfb88e02ca4aa2099ae50852c3de19a120e21fe7ec6a44fb49b41b1dde6f7"
},
"downloads": -1,
"filename": "onnxruntime_genai_cuda-0.5.1-cp311-cp311-win_amd64.whl",
"has_sig": false,
"md5_digest": "52beb375bfceacb78a5dabefdb24c453",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 14365313,
"upload_time": "2024-11-13T19:34:07",
"upload_time_iso_8601": "2024-11-13T19:34:07.727594Z",
"url": "https://files.pythonhosted.org/packages/fd/c6/42a19bc84117984a1a4c8bee0fc61e75ff972de1606a9d70d55041fbbf82/onnxruntime_genai_cuda-0.5.1-cp311-cp311-win_amd64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "81a38f22b451bd8ce913bb93c1a100402d6dd93dc6f623b16f544904cc95eb31",
"md5": "089f4c654e9182516948c881fb8daae9",
"sha256": "eb521213e12515172a0b742b1089facd03efb55d31b4eba8af2b55ce223d54dc"
},
"downloads": -1,
"filename": "onnxruntime_genai_cuda-0.5.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl",
"has_sig": false,
"md5_digest": "089f4c654e9182516948c881fb8daae9",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 15061326,
"upload_time": "2024-11-13T19:33:44",
"upload_time_iso_8601": "2024-11-13T19:33:44.731306Z",
"url": "https://files.pythonhosted.org/packages/81/a3/8f22b451bd8ce913bb93c1a100402d6dd93dc6f623b16f544904cc95eb31/onnxruntime_genai_cuda-0.5.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "eeda30cb1276d9613c80ec1890b3c93e8ca01dce21a3319edd72dc9f9b83700c",
"md5": "738f4f434039b53a341f07029df90465",
"sha256": "b42d15c9301f7ab9f8775f57c03eebaa243c6c8c866fdc127d2e320f79d35265"
},
"downloads": -1,
"filename": "onnxruntime_genai_cuda-0.5.1-cp312-cp312-win_amd64.whl",
"has_sig": false,
"md5_digest": "738f4f434039b53a341f07029df90465",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 14365466,
"upload_time": "2024-11-13T19:34:10",
"upload_time_iso_8601": "2024-11-13T19:34:10.067350Z",
"url": "https://files.pythonhosted.org/packages/ee/da/30cb1276d9613c80ec1890b3c93e8ca01dce21a3319edd72dc9f9b83700c/onnxruntime_genai_cuda-0.5.1-cp312-cp312-win_amd64.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-13 19:33:38",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "onnxruntime-genai-cuda"
}
JSON