diff --git a/uv.lock b/uv.lock index a2d3cf14..3a80d5c7 100644 --- a/uv.lock +++ b/uv.lock @@ -1207,7 +1207,7 @@ wheels = [ [[package]] name = "compressed-tensors" -version = "0.15.0.1" +version = "0.17.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "loguru" }, @@ -1217,9 +1217,9 @@ dependencies = [ { name = "transformers", version = "5.6.0", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-7-vec-inf-sglang'" }, { name = "transformers", version = "5.9.0", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-7-vec-inf-vllm'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/41/1b/c3c4a98ec5f2727656336f07a0c35862195c310d8eb0b2fa5b4be6848680/compressed_tensors-0.15.0.1.tar.gz", hash = "sha256:a8e93054e8a5ec49c980b09ed36c4c1249b4a8ee167920a8e461c4da26e78d99", size = 229412, upload-time = "2026-04-10T14:23:54.708Z" } +sdist = { url = "https://files.pythonhosted.org/packages/2c/9e/d7f18bd9a0354088abc11a0c1f2c7698f7c49e5a709faedf6a46e388f693/compressed_tensors-0.17.0.tar.gz", hash = "sha256:15c20d06bdbcf35b51fc99fd125e7b9be1e1855567c33b7a46dfac26ad6fb126", size = 257091, upload-time = "2026-06-03T16:49:17.208Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/a8/52/93833dc1610e017ac5b7dcd59b8304d8ef67d1114c2d124e728a2cbbea12/compressed_tensors-0.15.0.1-py3-none-any.whl", hash = "sha256:e1b1f322e82e475715e242bad46925a304ea8e5c98b5055a15b8eb22fb6bfea9", size = 194260, upload-time = "2026-04-10T14:23:53.098Z" }, + { url = "https://files.pythonhosted.org/packages/35/63/6edf0415b072fff0bf8b546074dea3f0f9b148e49b601ac98bdc60a76c68/compressed_tensors-0.17.0-py3-none-any.whl", hash = "sha256:4a1b89b508f7efb8ffb4eee8a6e69e0452d9b080cae130146025c64fbe9fa9aa", size = 211714, upload-time = "2026-06-03T16:49:15.672Z" }, ] [[package]] @@ -1646,6 +1646,13 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/2b/77/c13afad1a06824c1c942afd0205e78ff17f0ee06fc1a943f6e2135cf4112/cuda_tile-1.3.0-cp313-cp313-win_amd64.whl", hash = "sha256:efcb93c25563fe23d6aa083c22893fd703122eaf684b0d36874982d28a6dad0b", size = 240925, upload-time = "2026-04-20T15:52:21.283Z" }, ] +[package.optional-dependencies] +tileiras = [ + { name = "nvidia-cuda-nvcc", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, + { name = "nvidia-cuda-tileiras", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, + { name = "nvidia-nvvm", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, +] + [[package]] name = "cuda-toolkit" version = "13.0.2" @@ -2136,18 +2143,37 @@ wheels = [ [[package]] name = "fastsafetensors" -version = "0.3.1" +version = "0.5.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "typer" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/d2/69/e34a1e86a02b255896c57263bf0dfbae45b4708fd609b937f783c2202e7b/fastsafetensors-0.3.1.tar.gz", hash = "sha256:b7eb039a564d77280d17e5d63b27e9963ba5158ad02d2a3c1772c62072a81a53", size = 55665, upload-time = "2026-05-06T08:48:59.125Z" } -wheels = [ - { url = "https://files.pythonhosted.org/packages/0a/77/0913cd907585085b2f10f2d7eef2aa52c9445241dc66238de25ee24c8241/fastsafetensors-0.3.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:acc0971b006f381598d32c5f7aae3a07d9a10d87c701f26b65215083e15a4733", size = 1808292, upload-time = "2026-05-06T08:48:51.12Z" }, - { url = "https://files.pythonhosted.org/packages/e8/67/eaa10409a526242253926fe6981c652dfdb8aa4ec0d4cba4077a9376a1fd/fastsafetensors-0.3.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:32cf4b531b5d77de41d777106ea69036a16bdea80062646dabc93a11b4cf88ee", size = 1828304, upload-time = "2026-05-06T08:48:53.15Z" }, - { url = "https://files.pythonhosted.org/packages/6f/50/909871d673bacd6dfc7fee5e59bcd4ec9fbd19775bafe567ad236a3adced/fastsafetensors-0.3.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ac76f33e47959b7c31658fbbda1805df7540819828a3ce6a94eb34b4db0b1fa7", size = 1854825, upload-time = "2026-05-06T08:48:54.452Z" }, - { url = "https://files.pythonhosted.org/packages/84/f0/a9ec204e866b52ce323bafc31f4dbf15581b3c998d597ec53c62012716ff/fastsafetensors-0.3.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5c9f8d3e18969090b5d66581cb6e9f6c9057158c151ed87e9c309dead5c64442", size = 1854843, upload-time = "2026-05-06T08:48:55.921Z" }, - { url = "https://files.pythonhosted.org/packages/73/aa/00acc9e8f8209f513bf504371f0c40f4073b90240ef3e73507461d2390b9/fastsafetensors-0.3.1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:348814ad027891317ad8aff90a3c62f8f704a0861d089ea33cff088980602355", size = 1852255, upload-time = "2026-05-06T08:48:57.442Z" }, +sdist = { url = "https://files.pythonhosted.org/packages/9a/92/1deed9e83a70391666e906c71a6561f23e129b79fb5de05450d77488c258/fastsafetensors-0.5.0.tar.gz", hash = "sha256:2532cd58c779035eeadea4f8da8cd4340ba1d4a1a04753946e4f89aed2043c13", size = 128319, upload-time = "2026-10-17T14:49:08.936Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/ba/45/dd51c31243866815d5893da80fe8662f10eebf7823807c7c5263d5d668c5/fastsafetensors-0.5.0-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6f4063a7b351c365adb0a897a7cf034d83ffbefec50979fa637f40ae10b5a519", size = 2638444, upload-time = "2026-10-17T14:48:29.272Z" }, + { url = "https://files.pythonhosted.org/packages/45/b8/4f5b40aa9e7df6010fa3ba1fd0d36fcb2d0d3e74b96caa1d687710d34a7b/fastsafetensors-0.5.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c36fd85d0f28dd2ab335eeb3846d1751935babfae336c4b5a0dccec3e93b93cd", size = 2670743, upload-time = "2026-10-17T14:48:31.586Z" }, + { url = "https://files.pythonhosted.org/packages/cf/8a/2cb9d8ac02372622acfb93e740a3d43ccc25a5d3c1d887667ce955a5a1d7/fastsafetensors-0.5.0-cp310-cp310-win_amd64.whl", hash = "sha256:4096189c8d5f135f671c0e68906eecfcb3e154d5e255171f514de46e76d596d7", size = 508001, upload-time = "2026-10-17T14:48:32.896Z" }, + { url = "https://files.pythonhosted.org/packages/4f/5f/c08e4d86e52827c2f6cdf4ad9c4299a660ce414c1fe297ccdb6c42ab4c11/fastsafetensors-0.5.0-cp310-cp310-win_arm64.whl", hash = "sha256:59c57798ef435a866538e481682efb166bd5a1c3b9e73274ac43a07713beda5c", size = 710897, upload-time = "2026-10-17T14:48:34.279Z" }, + { url = "https://files.pythonhosted.org/packages/89/7b/fb2c2a369da1f37c502b3364bae95592139efc418762be6d5e71c1ac1605/fastsafetensors-0.5.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c2bf413b6569199db5fa436c0037dfa7e887e17b89ab49faf393398579646146", size = 2657157, upload-time = "2026-10-17T14:48:36.635Z" }, + { url = "https://files.pythonhosted.org/packages/2c/0e/24d7d618c20cbcc8167c502b5194a8c98ad62c75f32267ff42c12c59b6d0/fastsafetensors-0.5.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:33081163451a02e1ab80b1ba35459632e584bac79f301413a99fccb3699df426", size = 2688920, upload-time = "2026-10-17T14:48:38.353Z" }, + { url = "https://files.pythonhosted.org/packages/16/7d/2df4f1354b7eb42d3649da586f625b7ab29cdeef1fdba4e318e356efa45c/fastsafetensors-0.5.0-cp311-cp311-win_amd64.whl", hash = "sha256:2e2de360d7ab9d9c5bebe8d8a53b32dc1311ee70201f4b137515779125c89a4c", size = 509669, upload-time = "2026-10-17T14:48:39.718Z" }, + { url = "https://files.pythonhosted.org/packages/ff/b4/eae9a86554327991dea7b204ccc1efaefa8c4fecb83af9d92057add3295b/fastsafetensors-0.5.0-cp311-cp311-win_arm64.whl", hash = "sha256:1363303033fbb504146411baa60e4cf42803fe56a6f807cf85e98e0a238d9910", size = 711642, upload-time = "2026-10-17T14:48:41.529Z" }, + { url = "https://files.pythonhosted.org/packages/df/6d/01c61ec9f10decacf611d24287aaa12dffc8bb9efca006c1cf0f129beece/fastsafetensors-0.5.0-cp312-cp312-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:dff56f2e405948404703c5e14ef349b9b613def88ffbe6542602c592cad6dd94", size = 2689215, upload-time = "2026-10-17T14:48:43.368Z" }, + { url = "https://files.pythonhosted.org/packages/3a/e4/b3b9feac988f3b401789ab6e4f810487e2a844a5fc8dd3021e7a21f930ff/fastsafetensors-0.5.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:cf8085203d83abbf2ea37edfb4b007cf1de521ab1cd29b46935f611d68c80d7d", size = 2731897, upload-time = "2026-10-17T14:48:45.131Z" }, + { url = "https://files.pythonhosted.org/packages/c3/df/6c03ecf4a78d3771554c09d407d0f7669b4ec7320689af6d0a4552633f36/fastsafetensors-0.5.0-cp312-cp312-win_amd64.whl", hash = "sha256:4efadb3d1eb973845a64facee2dbd186d26ae551f8d0ca744fcec15934c90980", size = 511148, upload-time = "2026-10-17T14:48:46.591Z" }, + { url = "https://files.pythonhosted.org/packages/a5/d3/5a33ba57b1c0780ddbfb184a6f2ca8e7308159b2fe236d0c70510931d276/fastsafetensors-0.5.0-cp312-cp312-win_arm64.whl", hash = "sha256:ad0635c401c02da0945d3619172d9faddc1b54632def19fe039118c7b0cf4a5b", size = 708141, upload-time = "2026-10-17T14:48:48.019Z" }, + { url = "https://files.pythonhosted.org/packages/25/f1/80365dab6dfadd159e3987b38277216ea893ef0a956f78db77295d38ab7a/fastsafetensors-0.5.0-cp313-cp313-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8d5031896eb76bda48d3cc2d07318f3053bbb7640c6f70a9a6a783deba4ebe7d", size = 2689067, upload-time = "2026-10-17T14:48:49.678Z" }, + { url = "https://files.pythonhosted.org/packages/cf/71/e7f09de184c45b884040b14b285f42cacd9191bb624fd77e666a449b56d1/fastsafetensors-0.5.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:42704d63db61498afcd04cc18c4e35bfde461987be3efd28c54c02042eb54003", size = 2731145, upload-time = "2026-10-17T14:48:51.433Z" }, + { url = "https://files.pythonhosted.org/packages/e2/dd/d26e580eb42d771a135268e2afb0f737f67a0c1467b79d75dd611b10a2bc/fastsafetensors-0.5.0-cp313-cp313-win_amd64.whl", hash = "sha256:302e074c0c7a0f0287297ce19789561dd7b670880619d3c4ac35887fd6157f38", size = 511169, upload-time = "2026-10-17T14:48:53.278Z" }, + { url = "https://files.pythonhosted.org/packages/8a/04/df7b87b14051f1b85b492b1dbb569a9700d78cc6f6023b1ac4236ebea981/fastsafetensors-0.5.0-cp313-cp313-win_arm64.whl", hash = "sha256:43f729472a5fc9d8ce4d1db25c724b953dec76edf948dcdc2ad4c303abc4cd80", size = 708140, upload-time = "2026-10-17T14:48:54.928Z" }, + { url = "https://files.pythonhosted.org/packages/b2/30/d30cd3d75d8fd9908aab21c1d3f2ba6cdf89c182ce9e5b50bc6df43c28e8/fastsafetensors-0.5.0-cp314-cp314-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:cdf6d9ac44027372e344fcc3c2b8ad4c9ecc4b59269f5db1589f5fd23e6de218", size = 2687536, upload-time = "2026-10-17T14:48:56.296Z" }, + { url = "https://files.pythonhosted.org/packages/3e/6c/976bab2021c78a4e4a4748b9db4bd3ec356a53123a216e0748a1b9212e95/fastsafetensors-0.5.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:cff880ecd135818bd34296290ae4b98e2774a4c26d56bb772fc9afebc2fc854e", size = 2727287, upload-time = "2026-10-17T14:48:57.859Z" }, + { url = "https://files.pythonhosted.org/packages/ff/e3/3e53bb109f23f5be5b2355fca8f5cdaf63d883053d102b48a60c6312ca08/fastsafetensors-0.5.0-cp314-cp314-win_amd64.whl", hash = "sha256:c950d4825c87f21e91240ce7b1bd5b9f89c04e037396abba4810c4b506271676", size = 522725, upload-time = "2026-10-17T14:48:59.283Z" }, + { url = "https://files.pythonhosted.org/packages/4a/68/050bdfb9b710c47caf9fcc6b7269782c5a7fe3d0fd9578368634eb505392/fastsafetensors-0.5.0-cp314-cp314-win_arm64.whl", hash = "sha256:34e90f37ee587260559211eb6465be92891663ac38064692e02b06b07c4d20a3", size = 727345, upload-time = "2026-10-17T14:49:00.896Z" }, + { url = "https://files.pythonhosted.org/packages/84/fa/3a8d9bbc3b2b4b126bffb69f9f2cd2a870ff46c1b381c7461fa813a437d5/fastsafetensors-0.5.0-cp315-cp315-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c0eec60e95ebe08a05db2d3f7ab320eeec559c0559122f39bbc7eb30dcea3f35", size = 2688233, upload-time = "2026-10-17T14:49:02.566Z" }, + { url = "https://files.pythonhosted.org/packages/42/74/51411b9369c752a45b6cb2b3e431bdbd5accc11da8417485d046defeff11/fastsafetensors-0.5.0-cp315-cp315-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f4bf63b147c430d23eb86693e80bf6484f3870d4b4c5671c3f1a34f45c37b3fa", size = 2733245, upload-time = "2026-10-17T14:49:04.331Z" }, + { url = "https://files.pythonhosted.org/packages/46/81/0e97da1f585062164c815ac9b57f7aedf85e6c27dcb39dd47cea19e32dd3/fastsafetensors-0.5.0-cp315-cp315-win_amd64.whl", hash = "sha256:6111b5dbe857037eaaff7dc8973d3f61d6aec217759bdba2750fb2e26b1aeae0", size = 522725, upload-time = "2026-10-17T14:49:06.128Z" }, + { url = "https://files.pythonhosted.org/packages/de/94/224cb8b8e781e28b56da0715450fdd0381ad109bce6f540131e5c3931faa/fastsafetensors-0.5.0-cp315-cp315-win_arm64.whl", hash = "sha256:75fbf9f8559e1b0a8ab823741e56105ab784ec092ef25d118c18f726dd5b888c", size = 727313, upload-time = "2026-10-17T14:49:07.552Z" }, ] [[package]] @@ -2238,7 +2264,7 @@ wheels = [ [[package]] name = "flashinfer-cubin" -version = "0.6.11.post2" +version = "0.6.12" source = { registry = "https://pypi.org/simple" } resolution-markers = [ "python_full_version >= '3.14' and sys_platform == 'win32'", @@ -2255,7 +2281,7 @@ resolution-markers = [ "python_full_version < '3.11' and sys_platform != 'darwin'", ] wheels = [ - { url = "https://files.pythonhosted.org/packages/29/96/da75a9f61c64c87b16baa339fc8216a6c3743c5d263c555fded30fcbe6f7/flashinfer_cubin-0.6.11.post2-py3-none-any.whl", hash = "sha256:eb01c2801ee31d145bbf7afb2c223150333e602c8208216017b0190b1087b990", size = 360908523, upload-time = "2026-05-14T04:57:41.355Z" }, + { url = "https://files.pythonhosted.org/packages/7d/c6/63b1bb7b1a7ae612ecf53c0e568312c3d004f9f7558b0ab5edcf7900c360/flashinfer_cubin-0.6.12-py3-none-any.whl", hash = "sha256:01de132c493bb21d5df42ebe6890966cf83b40aa970dae06b2a3c0bed85f13ec", size = 447533460, upload-time = "2026-05-29T23:45:27.579Z" }, ] [[package]] @@ -2297,7 +2323,7 @@ wheels = [ [[package]] name = "flashinfer-python" -version = "0.6.11.post2" +version = "0.6.12" source = { registry = "https://pypi.org/simple" } resolution-markers = [ "python_full_version >= '3.14' and sys_platform == 'win32' and extra != 'extra-7-vec-inf-sglang' and extra == 'extra-7-vec-inf-vllm'", @@ -2320,7 +2346,7 @@ dependencies = [ { name = "apache-tvm-ffi", version = "0.1.9", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-7-vec-inf-vllm'" }, { name = "apache-tvm-ffi", version = "0.1.10", source = { registry = "https://pypi.org/simple" }, marker = "(extra != 'extra-7-vec-inf-sglang' and extra != 'extra-7-vec-inf-vllm') or (extra == 'extra-7-vec-inf-sglang' and extra == 'extra-7-vec-inf-vllm')" }, { name = "click", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, - { name = "cuda-tile", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, + { name = "cuda-tile", extra = ["tileiras"], marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, { name = "einops", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, { name = "ninja", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, { name = "numpy", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, @@ -2333,9 +2359,9 @@ dependencies = [ { name = "torch", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, { name = "tqdm", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/db/53/dbf2157f2bbb96d6f7a6891cf6abfb2e6e18963760a0c53e96c2de5c59db/flashinfer_python-0.6.11.post2.tar.gz", hash = "sha256:e9fdac56aea9f0f58a4e69b0645c54993760d3cc6c7bf5c2df4ce5a0aecc7953", size = 9248515, upload-time = "2026-05-14T04:57:32.83Z" } +sdist = { url = "https://files.pythonhosted.org/packages/61/d0/114a64319f5a804def2f307d5ed8f95e6d94a2acdacac4ed5f57525cbf46/flashinfer_python-0.6.12.tar.gz", hash = "sha256:bed67f9c46d81dd22611dfef2787998fc412b2fe2648d9e7d336861dda912694", size = 9453326, upload-time = "2026-05-29T23:45:16.466Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/c7/bc/518b092473f37d904ae07766ad37c772b93da13ea788777b22a80c3f1a7c/flashinfer_python-0.6.11.post2-py3-none-any.whl", hash = "sha256:550cbdb760f9f7ec0e42055e06636b9489d05f1a38989cafd77e6eb820de0138", size = 13746417, upload-time = "2026-05-14T04:57:30.25Z" }, + { url = "https://files.pythonhosted.org/packages/85/26/3ca33edbf64906603633cb91904798e427c0ac1c55a13707f8081708f3ae/flashinfer_python-0.6.12-py3-none-any.whl", hash = "sha256:0c7a01e586b4796810d974cbf13a9c0eb2ade6a94d12e3220cf7782a1c09b8d3", size = 13985243, upload-time = "2026-05-29T23:45:13.477Z" }, ] [[package]] @@ -2899,7 +2925,7 @@ wheels = [ [[package]] name = "humming-kernels" -version = "0.1.2" +version = "0.1.6" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "cuda-bindings" }, @@ -2913,9 +2939,9 @@ dependencies = [ { name = "tqdm" }, { name = "triton" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/06/f4/e141f45697b7d0d38bfaf8766a7362d8f0136e3cff2620624f24f68e2700/humming_kernels-0.1.2.tar.gz", hash = "sha256:7894c80061c7866591bef12617da720ac4e925636ffc99464af433a5dcb035eb", size = 117251, upload-time = "2026-05-23T16:18:08.084Z" } +sdist = { url = "https://files.pythonhosted.org/packages/29/5a/fbf574dcd83e9fea6aa3fa96b37bbdec40b8672407b1ed9679efa31fff1d/humming_kernels-0.1.6.tar.gz", hash = "sha256:882b9f382a010165a7cf8eecbad943bfe8d6b17566328fb57611c9a34bdccc9a", size = 214408, upload-time = "2026-06-20T04:04:43.221Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/6d/41/288bf756d921dbe98982eeb3ec4c20e7cb5224ea6dcb164f2df3d2f68a7f/humming_kernels-0.1.2-py3-none-any.whl", hash = "sha256:f7434b0424946445ef5ad5682bcabf309d97721818ed5bdc4c6f61de3c6b9d2f", size = 160951, upload-time = "2026-05-23T16:18:06.405Z" }, + { url = "https://files.pythonhosted.org/packages/25/85/490681b9ba24531da91d0bae801d2b26850e5a80bbd02c2efc500756e36b/humming_kernels-0.1.6-py3-none-any.whl", hash = "sha256:e64c0883fca930074bf920f4ba47cbf3acd244d7352f6c74c8d2182439770d8f", size = 178759, upload-time = "2026-06-20T04:04:41.66Z" }, ] [package.optional-dependencies] @@ -4130,7 +4156,7 @@ wheels = [ [[package]] name = "mistral-common" -version = "1.11.2" +version = "1.12.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "jsonschema" }, @@ -4144,9 +4170,9 @@ dependencies = [ { name = "typing-extensions", version = "4.15.0", source = { registry = "https://pypi.org/simple" }, marker = "(python_full_version >= '3.11' and extra == 'extra-7-vec-inf-sglang') or (python_full_version >= '3.11' and extra == 'extra-7-vec-inf-vllm') or (extra == 'extra-7-vec-inf-sglang' and extra == 'extra-7-vec-inf-vllm')" }, { name = "typing-extensions", version = "4.16.0", source = { registry = "https://pypi.org/simple" }, marker = "(python_full_version < '3.11' and extra == 'extra-7-vec-inf-sglang') or (python_full_version < '3.11' and extra == 'extra-7-vec-inf-vllm') or (extra == 'extra-7-vec-inf-sglang' and extra == 'extra-7-vec-inf-vllm')" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/c2/eb/12167a1bea9714582e5b4f539f9c019323363e314a499c72855ff0e5ad43/mistral_common-1.11.2.tar.gz", hash = "sha256:79f68fc2d1190f28637f40e053f919c8c2697e00b2aa679ddee562a95183f4ad", size = 6357845, upload-time = "2026-05-04T19:47:40.413Z" } +sdist = { url = "https://files.pythonhosted.org/packages/45/ee/e7860b0c9919a74fe43664f0bf19508df15243a27825aebc500b6c516d3b/mistral_common-1.12.0.tar.gz", hash = "sha256:d0f150926733cf422d4750ca19b47568df1f714557c9054a432b866f1f30bf52", size = 6416138, upload-time = "2026-09-22T15:17:56.43Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/47/f0/6a5d604b972e442b9d36c117d01788feddad099e4965699e3516ee6fefc3/mistral_common-1.11.2-py3-none-any.whl", hash = "sha256:ebb42062cd705a0aa2bc69b4cde2b83d446ae58150b7e29322c90cb08fcfca6c", size = 6531968, upload-time = "2026-05-04T19:47:37.718Z" }, + { url = "https://files.pythonhosted.org/packages/c0/78/2881bae14f5d79c6d4626439e74f1bc1591d0f10a9eb7eea5a408ecdb877/mistral_common-1.12.0-py3-none-any.whl", hash = "sha256:fa4504b66c30c0201ae4578c0340c5ee2abd22151c271532f62e373b985a53cf", size = 6580267, upload-time = "2026-09-22T15:17:53.665Z" }, ] [package.optional-dependencies] @@ -5049,17 +5075,17 @@ wheels = [ [[package]] name = "nvidia-cuda-nvcc" -version = "13.3.33" +version = "13.2.86" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-cuda-crt" }, - { name = "nvidia-cuda-runtime" }, - { name = "nvidia-nvvm" }, + { name = "nvidia-cuda-crt", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, + { name = "nvidia-cuda-runtime", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, + { name = "nvidia-nvvm", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, ] wheels = [ - { url = "https://files.pythonhosted.org/packages/be/b6/bb07a3a63b5b7b55516366747892abbf3ee62d616684c40bb51e6cbfe956/nvidia_cuda_nvcc-13.3.33-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8c348623b1434aebd234da9ec1f81022587ae4995d65c3dc8a7743245cc441f7", size = 39515074, upload-time = "2026-05-26T16:34:28.489Z" }, - { url = "https://files.pythonhosted.org/packages/3f/af/e1b107f034f7c133255c162b922bbad3da5be20ebf76df17662ae4bd31f6/nvidia_cuda_nvcc-13.3.33-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:53b5f1be1731574368b8be931b77b6313492266c464aef3dd3f431569ce90deb", size = 44943276, upload-time = "2026-05-26T16:35:05.912Z" }, - { url = "https://files.pythonhosted.org/packages/47/c2/831fa54020621a64d44cff47f1ed5eb0611794495fce01c857f6999d76b1/nvidia_cuda_nvcc-13.3.33-py3-none-win_amd64.whl", hash = "sha256:21c93aeef695a81b688137119f9120fe08a67292bf0ad730d94dc2b18bec23f0", size = 32723421, upload-time = "2026-05-26T17:01:47.511Z" }, + { url = "https://files.pythonhosted.org/packages/22/a3/403638f80960e677ae8ecc78059d8c85dc2519b85ed8c0229840dc6f3b54/nvidia_cuda_nvcc-13.2.86-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:909140a1f942b943982b2eff120e618c94e29d75d9e33f5cd074f0e64eb411e8", size = 38716270, upload-time = "2026-07-16T09:37:12.754Z" }, + { url = "https://files.pythonhosted.org/packages/38/7b/ad9b5f84e8820af24afa8db66b5b2785b9bdc3b8724dffcd5e6ef2d40e53/nvidia_cuda_nvcc-13.2.86-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:7d3f56c8d705bad35bbba69eb0470d90856fd5d4dc48c6a6173aaf1e9f887cf5", size = 44042846, upload-time = "2026-07-16T09:37:47.98Z" }, + { url = "https://files.pythonhosted.org/packages/03/c1/01dad23300993e52933773751d0dd8e795175daa830b798ce324db377e3a/nvidia_cuda_nvcc-13.2.86-py3-none-win_amd64.whl", hash = "sha256:4171face482ef8ca35b5b2d59cfd25d2d0e2a2e2534fe34d2ce20695437868d9", size = 31816369, upload-time = "2026-07-16T10:01:34.327Z" }, ] [[package]] @@ -5082,6 +5108,21 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/b7/94/6b867483bec07da24ffa32736c79fabb94ef3a7af4d787a9d4a974868576/nvidia_cuda_runtime-13.0.96-py3-none-win_amd64.whl", hash = "sha256:f79298c8a098cec150a597c8eba58ecdab96e3bdc4b9bc4f9983635031740492", size = 2927037, upload-time = "2025-10-09T09:04:23.782Z" }, ] +[[package]] +name = "nvidia-cuda-tileiras" +version = "13.2.86" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "nvidia-cuda-nvcc", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, + { name = "nvidia-nvjitlink", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, + { name = "nvidia-nvvm", marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, +] +wheels = [ + { url = "https://files.pythonhosted.org/packages/d0/a2/ade26f7fb55a5bb87815f7650660463d6601db411d5a9228f414b3ed5dfe/nvidia_cuda_tileiras-13.2.86-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5f79c6a9bf8583dae105cd67b985555f39f4576416664a86383ba892e8c346c9", size = 36418795, upload-time = "2026-07-16T09:43:35.006Z" }, + { url = "https://files.pythonhosted.org/packages/a4/ec/e01bcfe4f48fabd8fd1af139061a74f92f3b71fe3cac8a64e943157c2585/nvidia_cuda_tileiras-13.2.86-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:832f360aa8ce478ff878c4e6630cd767349a597ea54382e7c07a835b0daead96", size = 36970477, upload-time = "2026-07-16T09:44:08.421Z" }, + { url = "https://files.pythonhosted.org/packages/86/ba/3d8fefbaa2cf17545448064bbec72d32b1146165eb7b56be730af7a65a56/nvidia_cuda_tileiras-13.2.86-py3-none-win_amd64.whl", hash = "sha256:f1434762898ac914585aaa651ad0fe170c57bcdf8d878ba38343772998bb7ff3", size = 29384842, upload-time = "2026-07-16T10:04:45.813Z" }, +] + [[package]] name = "nvidia-cudnn-cu13" version = "9.19.0.56" @@ -5096,24 +5137,27 @@ wheels = [ [[package]] name = "nvidia-cudnn-frontend" -version = "1.18.0" -source = { registry = "https://pypi.org/simple" } -wheels = [ - { url = "https://files.pythonhosted.org/packages/86/be/f5a1e633c524c13c0182213ab27dab42dca29a3c785be5ff74d2d185aed1/nvidia_cudnn_frontend-1.18.0-cp310-cp310-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:baa6fbc8e7c55f1c78c0374ed9a890e1cf81acaca0c92d6135d18a8e3c985244", size = 2023500, upload-time = "2026-01-27T23:31:34.747Z" }, - { url = "https://files.pythonhosted.org/packages/82/a7/765a17c6a9496196c34f269d17dfb902b6c618c0261c0962511e95302e81/nvidia_cudnn_frontend-1.18.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2e4bcca42259e358002c8867e3624a558f66cd5dff2cc6c3aafd860ef2f41730", size = 2154278, upload-time = "2026-01-27T23:06:55.784Z" }, - { url = "https://files.pythonhosted.org/packages/19/a1/7caae2243540bc60e47eae95f0fd913c9baa05cf94df0471914f70d45158/nvidia_cudnn_frontend-1.18.0-cp310-cp310-win_amd64.whl", hash = "sha256:06252021ef1e5a7256f1e70429a426b01792636c05cc547fe8e64c6885a9652e", size = 1590158, upload-time = "2026-01-27T23:08:26.703Z" }, - { url = "https://files.pythonhosted.org/packages/e2/9a/83d3d080118de4a7810fa019349edec634b8b37b9cafaacd05719de62dd6/nvidia_cudnn_frontend-1.18.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f6d4d0b88d617b233a503c84980b54d840b60b2734497d1a7a071ec5293daec2", size = 2023709, upload-time = "2026-01-27T23:32:10.912Z" }, - { url = "https://files.pythonhosted.org/packages/13/c7/c3624b3ed77b102618f26295e816b27f1c3ebb1143730237a9f51d403c3f/nvidia_cudnn_frontend-1.18.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:382ea063b92cbfd5b442cb75ff8422932d78276aecf139e46713ed1ad3d07af4", size = 2155568, upload-time = "2026-01-27T23:07:13.277Z" }, - { url = "https://files.pythonhosted.org/packages/52/dd/8613dfd029d076b86a8a87efe3f4bb4ab73cec15fa8fc27e665098f4d167/nvidia_cudnn_frontend-1.18.0-cp311-cp311-win_amd64.whl", hash = "sha256:baa509effc4d299d3f04e549d4188f88bca8a8b527f483cbd2f66bc18f13a8b1", size = 1591244, upload-time = "2026-01-27T23:08:44.691Z" }, - { url = "https://files.pythonhosted.org/packages/e3/b4/604e230378680ee117849a4e1045baca092f93161a829291a84d5acce70c/nvidia_cudnn_frontend-1.18.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:310b417f2848a83d1437203fcaeea320a74fb7f28af20bf42bf5afc9c01f1c12", size = 2027408, upload-time = "2026-01-27T23:32:46.576Z" }, - { url = "https://files.pythonhosted.org/packages/c6/52/08f98262e77b1cbcc834cc1a5db494d0661ea1dbdea58c2e2d51a57fdaca/nvidia_cudnn_frontend-1.18.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:6c023539ca6de99234cf5102c3ec0d6af817f5396fc93028a22ba5b834a35b8a", size = 2159245, upload-time = "2026-01-27T23:07:32.664Z" }, - { url = "https://files.pythonhosted.org/packages/aa/1f/751a5a8cfdc95fb4dc556192d37369ae488c30c473fe9a3ec720b23d07ea/nvidia_cudnn_frontend-1.18.0-cp312-cp312-win_amd64.whl", hash = "sha256:e13f7dd46cdb4762dde87f181f06d1c5e15e9478bbdd547bfa74d9b11f415aae", size = 1591041, upload-time = "2026-01-27T23:09:04.118Z" }, - { url = "https://files.pythonhosted.org/packages/e8/bd/db791a26ebb6a6e1268f518e18c82d8ad18546f7008f4b0d5bde15f927de/nvidia_cudnn_frontend-1.18.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5a6e2b7bd43705ffa4af3b187374fdd5e7d09fc228a4d65fc8b4b0a537a8e605", size = 2027249, upload-time = "2026-01-27T23:33:22.46Z" }, - { url = "https://files.pythonhosted.org/packages/19/74/3038cf496d5de7cfdff730f5202e438c17d9123de507059340e02ddff9d7/nvidia_cudnn_frontend-1.18.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c0544206b02cae9da4f044ca3fe7416b99e0c8a8052285dd3e5a8fc445d34f9c", size = 2160001, upload-time = "2026-01-27T23:07:50.248Z" }, - { url = "https://files.pythonhosted.org/packages/a1/5e/148cc6609dba326e620e4d949246020dfba05ca07d0387442e62b71d19b6/nvidia_cudnn_frontend-1.18.0-cp313-cp313-win_amd64.whl", hash = "sha256:7eefa5f10cc003df5f3593f82f1ee6c001fc3412bdc78430c751914dfceefd7f", size = 1591270, upload-time = "2026-01-27T23:09:21.435Z" }, - { url = "https://files.pythonhosted.org/packages/a3/0a/515209dd2afc6027bf1112bf415f575bfe9628d18877abe7424cb597dd7b/nvidia_cudnn_frontend-1.18.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b489da1b30f1d7da822b37b89cc4f68afd80e020eb57e4ab24921f8b57f6e946", size = 2028689, upload-time = "2026-02-11T21:32:04.235Z" }, - { url = "https://files.pythonhosted.org/packages/ab/57/52d18e1f50979eeabfafb408ec73068afc5a1e1ccd21636240317cd456d4/nvidia_cudnn_frontend-1.18.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:37688c81a34ac590aff9de4c34d2968bab949411af707baa327616ebd4b34ae1", size = 2160182, upload-time = "2026-02-11T21:25:18.437Z" }, - { url = "https://files.pythonhosted.org/packages/67/53/df2810b56d259ef96fa6beaa1381bd14c29fbe82836b409516e864c5e177/nvidia_cudnn_frontend-1.18.0-cp314-cp314-win_amd64.whl", hash = "sha256:5053b473fa74168b5fbf35934cd6187f88aa03b8447b9f2cd417332d5e5c9569", size = 1592759, upload-time = "2026-02-11T21:32:33.87Z" }, +version = "1.28.0" +source = { registry = "https://pypi.org/simple" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/ee/75/d0069a6cdc600fa4b61ec0250dda54f410db2a4331c943ba9c979753d0a1/nvidia_cudnn_frontend-1.28.0-cp310-cp310-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:fcd16141cae7b013ad0a9fd4beda74bb8ee15b66841ebecacaa4179af0975f4b", size = 5505352, upload-time = "2026-09-02T06:04:54.583Z" }, + { url = "https://files.pythonhosted.org/packages/03/8a/6a6ba2363c31065150b00441e13fd2bc933fedc89b7bd29b74aea41c4179/nvidia_cudnn_frontend-1.28.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2c92499c388665ab93a492705c591856f8c04014f5dac0e2fb593355bc0d888f", size = 5670521, upload-time = "2026-09-02T06:05:11.712Z" }, + { url = "https://files.pythonhosted.org/packages/0e/cb/2226a911a61b754846cf207282c72653a9a3d0cc20d31f9d00204edede73/nvidia_cudnn_frontend-1.28.0-cp310-cp310-win_amd64.whl", hash = "sha256:c9d2358dcee1d94676f74147996f4d5397124a6569da52f84f0088183811a17f", size = 5012307, upload-time = "2026-09-02T06:05:35.274Z" }, + { url = "https://files.pythonhosted.org/packages/b2/55/880914d0c16bedce1c5ed185ce0847eee8c6fe6c5104a2698ace8ce93a2b/nvidia_cudnn_frontend-1.28.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5173437c88b3accb7cc6855b42a64d583d7962ce5a90b148257e0a0d3c9c1eaa", size = 5509420, upload-time = "2026-09-02T06:06:00.48Z" }, + { url = "https://files.pythonhosted.org/packages/25/9e/f65832a9bffec31ac9f55edf18c25c3c8a396ddafd89c108fe21389552c4/nvidia_cudnn_frontend-1.28.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:248e2d81fb670e7b591246eeb626fc336e2bad29551afa84daf062d63aaf76b3", size = 5671671, upload-time = "2026-09-02T06:06:19.418Z" }, + { url = "https://files.pythonhosted.org/packages/c4/8d/07e7665fb1f08fa9c318e9fee1e0e677f29e56b3c6eb0a5aa43c1ccfa272/nvidia_cudnn_frontend-1.28.0-cp311-cp311-win_amd64.whl", hash = "sha256:bf585cebdbf2aebd2aacfb9b0630a2db2432b4efe9be8c6cd103980c931e2c31", size = 5013324, upload-time = "2026-09-02T06:06:43.819Z" }, + { url = "https://files.pythonhosted.org/packages/d1/9e/33b746b800c36a8aae8432605c5b2af6cc5fc683cc1a6954a084c3853690/nvidia_cudnn_frontend-1.28.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:060b0c021f6841312ad26dd837a51b4941d4e0d2a547d87455bd974c173da075", size = 5512380, upload-time = "2026-09-02T06:07:11.74Z" }, + { url = "https://files.pythonhosted.org/packages/fd/0d/b6670b5d2d193322e0765d01889998df11d7f57522f210dc808b456530d9/nvidia_cudnn_frontend-1.28.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:335c916be758a8d5533104e04fc4a15f9c30a419b103ecd2b6fd0d23e1d532e4", size = 5677342, upload-time = "2026-09-02T06:07:31.949Z" }, + { url = "https://files.pythonhosted.org/packages/87/14/4c47521e4dfcebc1e6c59f23942c0aa1d73e3385c1a2a9b16f41c6d3b506/nvidia_cudnn_frontend-1.28.0-cp312-cp312-win_amd64.whl", hash = "sha256:e1929bde04d0172828b65584317b5e2de3e60743768e5f634875f69eeab6b97e", size = 5016827, upload-time = "2026-09-02T06:07:50.919Z" }, + { url = "https://files.pythonhosted.org/packages/1b/37/ce841fc013bc01de87d33eba58ba386477e411f31e3e41337d3f745ea1f3/nvidia_cudnn_frontend-1.28.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:30e20178e46a5a5049c2358f4147d1c5414b45b2753a455da05bab914807a44d", size = 5512441, upload-time = "2026-09-02T06:08:14.921Z" }, + { url = "https://files.pythonhosted.org/packages/3d/1a/51fa7f3d4fd8377d7acdf99e92d33a38be83979897360ca36b6f3521e92d/nvidia_cudnn_frontend-1.28.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:26cd299d202e832a1d562510d6844dc7c6f256cb1b4f0f29d5b2fa0b34f05e98", size = 5677523, upload-time = "2026-09-02T06:08:37.287Z" }, + { url = "https://files.pythonhosted.org/packages/2f/c3/a8073be9a425399da5d4ec6bc080d9b5fdc0ef276921c499821937769c24/nvidia_cudnn_frontend-1.28.0-cp313-cp313-win_amd64.whl", hash = "sha256:33884611aa659687138d6abf3a10a5e121cd76018192a14c69be43e8898da384", size = 5016995, upload-time = "2026-09-02T06:09:03.333Z" }, + { url = "https://files.pythonhosted.org/packages/79/21/dc09de787243c3333d6b958eca44697bfd56951465182373d37d88dec0e8/nvidia_cudnn_frontend-1.28.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:851fde83b08026f33fc83b2c656232833e4c79ad886c937ed5a035473ad02e1d", size = 5514494, upload-time = "2026-09-02T06:09:23.829Z" }, + { url = "https://files.pythonhosted.org/packages/e5/31/f6e3c1983cae0da1759c7bb6a57f4b2208b042a24b7ccaad775dd14601e0/nvidia_cudnn_frontend-1.28.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:56c596054d7ff929ba95ae560bcf1f41d4f0113a9f8b693401c0d508262a4717", size = 5679104, upload-time = "2026-09-02T06:09:44.703Z" }, + { url = "https://files.pythonhosted.org/packages/b9/b8/3ed83bb8cf6a8c5fd8511883b5b65b2f7cfd50a655626cd4ffb4416b6729/nvidia_cudnn_frontend-1.28.0-cp314-cp314-win_amd64.whl", hash = "sha256:3d4a7a8b33b6c32018162b10b0f8b2d5046ac224c7fcf4765f4562419c3e559e", size = 5015543, upload-time = "2026-09-02T06:10:07.694Z" }, + { url = "https://files.pythonhosted.org/packages/32/4a/73a453003eb527565b9a5b0b117ec04a75b4eddd0a0796027064d87b77f2/nvidia_cudnn_frontend-1.28.0-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:92d52770600d9b175e3098faed570477cf31c78646dc224cd92b2149d62afe0e", size = 5517650, upload-time = "2026-09-02T06:10:30.932Z" }, + { url = "https://files.pythonhosted.org/packages/a5/29/742fd93110343da4451eb4d1a713f6291bbb4e80e7b91fae91c826cc150c/nvidia_cudnn_frontend-1.28.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:04b209c40cf5295ea6141be8c74c2e65449b619a0911ceb2ae27cd914124d376", size = 5680701, upload-time = "2026-09-02T06:10:55.184Z" }, + { url = "https://files.pythonhosted.org/packages/92/79/7a341c7eb5252673f7117d77ec6615264c6d2cb08c767ec4665fc722e7c7/nvidia_cudnn_frontend-1.28.0-cp314-cp314t-win_amd64.whl", hash = "sha256:8fe9ab83ac4e14069d0904b5e3dc8307904c583ebe53ce941dacd534b7e8df6e", size = 5042699, upload-time = "2026-09-02T06:11:19.176Z" }, ] [[package]] @@ -5420,6 +5464,7 @@ source = { registry = "https://pypi.org/simple" } wheels = [ { url = "https://files.pythonhosted.org/packages/56/7a/123e033aaff487c77107195fa5a2b8686795ca537935a24efae476c41f05/nvidia_nvjitlink-13.0.88-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:13a74f429e23b921c1109976abefacc69835f2f433ebd323d3946e11d804e47b", size = 40713933, upload-time = "2025-09-04T08:35:43.553Z" }, { url = "https://files.pythonhosted.org/packages/ab/2c/93c5250e64df4f894f1cbb397c6fd71f79813f9fd79d7cd61de3f97b3c2d/nvidia_nvjitlink-13.0.88-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:e931536ccc7d467a98ba1d8b89ff7fa7f1fa3b13f2b0069118cd7f47bff07d0c", size = 38768748, upload-time = "2025-09-04T08:35:20.008Z" }, + { url = "https://files.pythonhosted.org/packages/e4/01/07530b0e37546231052e30234540289c42eaffa486f1a34a87fed340157b/nvidia_nvjitlink-13.0.88-py3-none-win_amd64.whl", hash = "sha256:634e96e3da9ef845ae744097a1f289238ecf946ce0b82e93cdce14b9782e682f", size = 36035115, upload-time = "2025-09-04T08:43:03.001Z" }, ] [[package]] @@ -5442,12 +5487,12 @@ wheels = [ [[package]] name = "nvidia-nvvm" -version = "13.3.33" +version = "13.2.86" source = { registry = "https://pypi.org/simple" } wheels = [ - { url = "https://files.pythonhosted.org/packages/01/8a/f767031dcd0d24c2bbab4b696dbcf004da4f3284e5e4649fc47bc0e2bb78/nvidia_nvvm-13.3.33-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:aafaf73246b6126bc88f521e5dab1d196395ee87739d9f5b7c39c9fee0ead9c7", size = 69250604, upload-time = "2026-05-26T16:57:56.875Z" }, - { url = "https://files.pythonhosted.org/packages/83/36/ce0d42d3a4465c858c379932f0080d29d22f04383ab79119c7c4f4cdd5ef/nvidia_nvvm-13.3.33-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:fd74a1c5ef284ba04c1ba75f886404dff953c54731a3a9c7b45e9aedaf1a226b", size = 66984524, upload-time = "2026-05-26T16:57:30.778Z" }, - { url = "https://files.pythonhosted.org/packages/8f/96/4de7a37803d168337ab36f81ecbc496c7c21c9b06ec68ce0ecc381af88d4/nvidia_nvvm-13.3.33-py3-none-win_amd64.whl", hash = "sha256:b1c63cf8972d8a1ff153c5ac4cc7038fe6ef705aa38415f12007b0e5e4c31b79", size = 60175824, upload-time = "2026-05-26T17:13:27.588Z" }, + { url = "https://files.pythonhosted.org/packages/c7/1d/b50325516e259d4de9fca78b069840d39b6a172c5ba012b88d9985e01fa3/nvidia_nvvm-13.2.86-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:a9244f3209922d655612c11ebb4117ea1f80983cb2b215c9cccded127282cebc", size = 64280112, upload-time = "2026-07-16T09:58:27.625Z" }, + { url = "https://files.pythonhosted.org/packages/e6/64/039ad70d68355634581d3b66f99b7aa8f75ca6078e1a6a2c9223677bbee3/nvidia_nvvm-13.2.86-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:a502dcc2859f17a925adba495c222d44a221b9eb10e7d111a7046dc2cc883b69", size = 61886756, upload-time = "2026-07-16T09:57:51.818Z" }, + { url = "https://files.pythonhosted.org/packages/c8/1c/a1e27ca53d767f5043eab9332564581e976953a437e1bc8c3642679a622f/nvidia_nvvm-13.2.86-py3-none-win_amd64.whl", hash = "sha256:7d140c2dd2d177af71240a31bbca20f40b4aee9a4e331156083e387855222b49", size = 56750837, upload-time = "2026-07-16T10:11:39.216Z" }, ] [[package]] @@ -10021,7 +10066,7 @@ inference = [ { name = "ax-platform", version = "1.2.4", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11'" }, { name = "cupy-cuda12x" }, { name = "flashinfer-python", version = "0.6.11.post1", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-7-vec-inf-sglang'" }, - { name = "flashinfer-python", version = "0.6.11.post2", source = { registry = "https://pypi.org/simple" }, marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, + { name = "flashinfer-python", version = "0.6.12", source = { registry = "https://pypi.org/simple" }, marker = "extra != 'extra-7-vec-inf-sglang' or extra == 'extra-7-vec-inf-vllm'" }, { name = "py3nvml" }, { name = "torch" }, { name = "wandb" }, @@ -10109,7 +10154,7 @@ wheels = [ [[package]] name = "vllm" -version = "0.22.0" +version = "0.24.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "aiohttp" }, @@ -10127,11 +10172,11 @@ dependencies = [ { name = "fastsafetensors" }, { name = "filelock", version = "4.1.0", source = { registry = "https://pypi.org/simple" }, marker = "(python_full_version < '3.11' and extra == 'extra-7-vec-inf-vllm') or (extra == 'extra-7-vec-inf-sglang' and extra == 'extra-7-vec-inf-vllm')" }, { name = "filelock", version = "4.2.4", source = { registry = "https://pypi.org/simple" }, marker = "(python_full_version >= '3.11' and extra == 'extra-7-vec-inf-vllm') or (extra == 'extra-7-vec-inf-sglang' and extra == 'extra-7-vec-inf-vllm')" }, - { name = "flashinfer-cubin", version = "0.6.11.post2", source = { registry = "https://pypi.org/simple" } }, - { name = "flashinfer-python", version = "0.6.11.post2", source = { registry = "https://pypi.org/simple" } }, - { name = "gguf" }, + { name = "flashinfer-cubin", version = "0.6.12", source = { registry = "https://pypi.org/simple" } }, + { name = "flashinfer-python", version = "0.6.12", source = { registry = "https://pypi.org/simple" } }, { name = "humming-kernels", extra = ["cu13"], marker = "extra == 'extra-7-vec-inf-vllm'" }, { name = "ijson" }, + { name = "jsonschema" }, { name = "lark" }, { name = "llguidance", version = "1.7.6", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine == 'aarch64' or platform_machine == 'arm64' or platform_machine == 'ppc64le' or platform_machine == 'x86_64'" }, { name = "lm-format-enforcer" }, @@ -10173,6 +10218,7 @@ dependencies = [ { name = "setproctitle" }, { name = "setuptools", marker = "python_full_version >= '3.12'" }, { name = "six", marker = "python_full_version >= '3.12'" }, + { name = "starlette" }, { name = "tiktoken" }, { name = "tilelang", version = "0.1.9", source = { registry = "https://pypi.org/simple" } }, { name = "tokenizers" }, @@ -10187,10 +10233,10 @@ dependencies = [ { name = "watchfiles" }, { name = "xgrammar", version = "0.2.1", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine == 'aarch64' or platform_machine == 'arm64' or platform_machine == 'ppc64le' or platform_machine == 's390x' or platform_machine == 'x86_64'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/e2/bf/46631fd8e2e9d81c5abe2ab923e5367754bc0cad685c4ddac1d5d86d91b5/vllm-0.22.0.tar.gz", hash = "sha256:6d41581a9e5288cd69278518a550c6d7ce510ae27a506556a3427d01284be7fe", size = 36239170, upload-time = "2026-05-29T10:35:39.448Z" } +sdist = { url = "https://files.pythonhosted.org/packages/d4/17/ea541f9ffb31d438ed6a5a8e1f7b9805410664abf97e326f28416147a5da/vllm-0.24.0.tar.gz", hash = "sha256:0862453adc1f3339f1a0c9dca1179c34d6ed6e118f87b6e5bddd120af614ac66", size = 37236989, upload-time = "2026-06-30T01:18:35.996Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/ed/e8/05a69dbd7416c5a5ac91f51e626fede9ceeabe9c6fe243fc11e2b3e1ad3e/vllm-0.22.0-cp38-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:0fbe1ff32e9ad82c56b002de11b061ca6b5b8a256cd11473946d2222115ed267", size = 252942448, upload-time = "2026-05-29T10:32:10.261Z" }, - { url = "https://files.pythonhosted.org/packages/ca/23/3f7f759763fb9b4cf5787bcb4a43f74904f8e644d53d4fdb4e19654a92fd/vllm-0.22.0-cp38-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:c387a977e35795e8f77b009e019e69722963819c26b55e4a679e09d4279ae35d", size = 261034920, upload-time = "2026-05-29T10:33:10.357Z" }, + { url = "https://files.pythonhosted.org/packages/9e/80/51a071305b4eed0f6f512dc1c1c6957cbb14ccce38db1be90ffcff2a2844/vllm-0.24.0-cp38-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:700db71c3cf14697d42583521f38b12fac38db1e7a8ad062e8e4d63a5dadebd5", size = 271361241, upload-time = "2026-06-30T01:17:52.566Z" }, + { url = "https://files.pythonhosted.org/packages/00/33/3f0abda52acff437a471cf3a2bf204213eb4102975b2677512cd76f2b45e/vllm-0.24.0-cp38-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:2d2831aeba311292250df0132dbc4d8e9f42c654536eaec48e6fe58acb1822cf", size = 279209310, upload-time = "2026-06-30T01:18:18.504Z" }, ] [package.optional-dependencies] @@ -10200,6 +10246,7 @@ audio = [ { name = "scipy", version = "1.15.3", source = { registry = "https://pypi.org/simple" }, marker = "(python_full_version < '3.11' and extra == 'extra-7-vec-inf-vllm') or (extra == 'extra-7-vec-inf-sglang' and extra == 'extra-7-vec-inf-vllm')" }, { name = "scipy", version = "1.17.1", source = { registry = "https://pypi.org/simple" }, marker = "(python_full_version >= '3.11' and extra == 'extra-7-vec-inf-vllm') or (extra == 'extra-7-vec-inf-sglang' and extra == 'extra-7-vec-inf-vllm')" }, { name = "soundfile" }, + { name = "soxr" }, ] bench = [ { name = "datasets" },