xinference 0.7.5__py3-none-any.whl → 0.8.1__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of xinference might be problematic. Click here for more details.
- xinference/_version.py +3 -3
- xinference/api/oauth2/__init__.py +13 -0
- xinference/api/oauth2/common.py +14 -0
- xinference/api/oauth2/core.py +93 -0
- xinference/api/oauth2/types.py +36 -0
- xinference/api/oauth2/utils.py +44 -0
- xinference/api/restful_api.py +216 -27
- xinference/client/oscar/actor_client.py +18 -18
- xinference/client/restful/restful_client.py +96 -33
- xinference/conftest.py +63 -1
- xinference/constants.py +1 -0
- xinference/core/chat_interface.py +143 -3
- xinference/core/metrics.py +83 -0
- xinference/core/model.py +244 -181
- xinference/core/status_guard.py +86 -0
- xinference/core/supervisor.py +57 -7
- xinference/core/worker.py +134 -13
- xinference/deploy/cmdline.py +142 -16
- xinference/deploy/local.py +39 -7
- xinference/deploy/supervisor.py +2 -0
- xinference/deploy/worker.py +33 -5
- xinference/fields.py +4 -1
- xinference/model/core.py +8 -1
- xinference/model/embedding/core.py +3 -2
- xinference/model/embedding/model_spec_modelscope.json +60 -18
- xinference/model/image/stable_diffusion/core.py +4 -3
- xinference/model/llm/__init__.py +7 -0
- xinference/model/llm/ggml/llamacpp.py +3 -2
- xinference/model/llm/llm_family.json +87 -3
- xinference/model/llm/llm_family.py +15 -5
- xinference/model/llm/llm_family_modelscope.json +92 -3
- xinference/model/llm/pytorch/chatglm.py +70 -28
- xinference/model/llm/pytorch/core.py +11 -30
- xinference/model/llm/pytorch/internlm2.py +155 -0
- xinference/model/llm/pytorch/utils.py +0 -153
- xinference/model/llm/utils.py +37 -8
- xinference/model/llm/vllm/core.py +15 -3
- xinference/model/multimodal/__init__.py +15 -8
- xinference/model/multimodal/core.py +8 -1
- xinference/model/multimodal/model_spec.json +9 -0
- xinference/model/multimodal/model_spec_modelscope.json +45 -0
- xinference/model/multimodal/qwen_vl.py +5 -9
- xinference/model/utils.py +7 -2
- xinference/types.py +2 -0
- xinference/web/ui/build/asset-manifest.json +3 -3
- xinference/web/ui/build/index.html +1 -1
- xinference/web/ui/build/static/js/main.b83095c2.js +3 -0
- xinference/web/ui/build/static/js/{main.236e72e7.js.LICENSE.txt → main.b83095c2.js.LICENSE.txt} +7 -0
- xinference/web/ui/build/static/js/main.b83095c2.js.map +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/0a853b2fa1902551e262a2f1a4b7894341f27b3dd9587f2ef7aaea195af89518.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/101923c539819f26ad11fbcbd6f6e56436b285efbb090dcc7dd648c6e924c4a8.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/193e7ba39e70d4bb2895a5cb317f6f293a5fd02e7e324c02a1eba2f83216419c.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/22858de5265f2d279fca9f2f54dfb147e4b2704200dfb5d2ad3ec9769417328f.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/27696db5fcd4fcf0e7974cadf1e4a2ab89690474045c3188eafd586323ad13bb.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/27bcada3ee8f89d21184b359f022fc965f350ffaca52c9814c29f1fc37121173.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/27bdbe25deab8cf08f7fab8f05f8f26cf84a98809527a37986a4ab73a57ba96a.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/2bee7b8bd3d52976a45d6068e1333df88b943e0e679403c809e45382e3818037.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/30670751f55508ef3b861e13dd71b9e5a10d2561373357a12fc3831a0b77fd93.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/3605cd3a96ff2a3b443c70a101575482279ad26847924cab0684d165ba0d2492.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/3789ef437d3ecbf945bb9cea39093d1f16ebbfa32dbe6daf35abcfb6d48de6f1.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/4942da6bc03bf7373af068e22f916341aabc5b5df855d73c1d348c696724ce37.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/4d933e35e0fe79867d3aa6c46db28804804efddf5490347cb6c2c2879762a157.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/4d96f071168af43965e0fab2ded658fa0a15b8d9ca03789a5ef9c5c16a4e3cee.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/4fd24800544873512b540544ae54601240a5bfefd9105ff647855c64f8ad828f.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/52a6136cb2dbbf9c51d461724d9b283ebe74a73fb19d5df7ba8e13c42bd7174d.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/5c408307c982f07f9c09c85c98212d1b1c22548a9194c69548750a3016b91b88.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/663adbcb60b942e9cf094c8d9fabe57517f5e5e6e722d28b4948a40b7445a3b8.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/666bb2e1b250dc731311a7e4880886177885dfa768508d2ed63e02630cc78725.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/71493aadd34d568fbe605cacaba220aa69bd09273251ee4ba27930f8d01fccd8.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/8b071db2a5a9ef68dc14d5f606540bd23d9785e365a11997c510656764d2dccf.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/8b246d79cd3f6fc78f11777e6a6acca6a2c5d4ecce7f2dd4dcf9a48126440d3c.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/8d33354bd2100c8602afc3341f131a88cc36aaeecd5a4b365ed038514708e350.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/95c8cc049fadd23085d8623e1d43d70b614a4e52217676f186a417dca894aa09.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/a4d72d3b806ba061919115f0c513738726872e3c79cf258f007519d3f91d1a16.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/a8070ce4b780b4a044218536e158a9e7192a6c80ff593fdc126fee43f46296b5.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/b4e4fccaf8f2489a29081f0bf3b191656bd452fb3c8b5e3c6d92d94f680964d5.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/b53eb7c7967f6577bd3e678293c44204fb03ffa7fdc1dd59d3099015c68f6f7f.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/bd04667474fd9cac2983b03725c218908a6cc0ee9128a5953cd00d26d4877f60.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/c230a727b8f68f0e62616a75e14a3d33026dc4164f2e325a9a8072d733850edb.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/d06af85a84e5c5a29d3acf2dbb5b30c0cf75c8aec4ab5f975e6096f944ee4324.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/d44a6eb6106e09082b691a315c9f6ce17fcfe25beb7547810e0d271ce3301cd2.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/d5e150bff31715977d8f537c970f06d4fe3de9909d7e8342244a83a9f6447121.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/de36e5c08fd524e341d664883dda6cb1745acc852a4f1b011a35a0b4615f72fa.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/f037ffef5992af0892d6d991053c1dace364cd39a3f11f1a41f92776e8a59459.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/f23ab356a8603d4a2aaa74388c2f381675c207d37c4d1c832df922e9655c9a6b.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/f7c23b0922f4087b9e2e3e46f15c946b772daa46c28c3a12426212ecaf481deb.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/f95a8bd358eeb55fa2f49f1224cc2f4f36006359856744ff09ae4bb295f59ec1.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/fe5db70859503a54cbe71f9637e5a314cda88b1f0eecb733b6e6f837697db1ef.json +1 -0
- xinference/web/ui/node_modules/.package-lock.json +36 -0
- xinference/web/ui/node_modules/@types/cookie/package.json +30 -0
- xinference/web/ui/node_modules/@types/hoist-non-react-statics/package.json +33 -0
- xinference/web/ui/node_modules/react-cookie/package.json +55 -0
- xinference/web/ui/node_modules/universal-cookie/package.json +48 -0
- xinference/web/ui/package-lock.json +37 -0
- xinference/web/ui/package.json +3 -2
- {xinference-0.7.5.dist-info → xinference-0.8.1.dist-info}/METADATA +17 -6
- {xinference-0.7.5.dist-info → xinference-0.8.1.dist-info}/RECORD +101 -66
- xinference/web/ui/build/static/js/main.236e72e7.js +0 -3
- xinference/web/ui/build/static/js/main.236e72e7.js.map +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/0cccfbe5d963b8e31eb679f9d9677392839cedd04aa2956ac6b33cf19599d597.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/0f3b6cc71b7c83bdc85aa4835927aeb86af2ce0d2ac241917ecfbf90f75c6d27.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/2f651cf60b1bde50c0601c7110f77dd44819fb6e2501ff748a631724d91445d4.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/42bb623f337ad08ed076484185726e072ca52bb88e373d72c7b052db4c273342.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/57af83639c604bd3362d0f03f7505e81c6f67ff77bee7c6bb31f6e5523eba185.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/667753ce39ce1d4bcbf9a5f1a103d653be1d19d42f4e1fbaceb9b507679a52c7.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/66ed1bd4c06748c1b176a625c25c856997edc787856c73162f82f2b465c5d956.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/78f2521da2e2a98b075a2666cb782c7e2c019cd3c72199eecd5901c82d8655df.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/8d2b0b3c6988d1894694dcbbe708ef91cfe62d62dac317031f09915ced637953.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/9427ae7f1e94ae8dcd2333fb361e381f4054fde07394fe5448658e3417368476.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/bcee2b4e76b07620f9087989eb86d43c645ba3c7a74132cf926260af1164af0e.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/cc2ddd02ccc1dad1a2737ac247c79e6f6ed2c7836c6b68e511e3048f666b64af.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/d2e8e6665a7efc832b43907dadf4e3c896a59eaf8129f9a520882466c8f2e489.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/d8a42e9df7157de9f28eecefdf178fd113bf2280d28471b6e32a8a45276042df.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/e26750d9556e9741912333349e4da454c53dbfddbfc6002ab49518dcf02af745.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/ef42ec014d7bc373b874b2a1ff0dcd785490f125e913698bc049b0bd778e4d66.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/fe3eb4d76c79ca98833f686d642224eeeb94cc83ad14300d281623796d087f0a.json +0 -1
- {xinference-0.7.5.dist-info → xinference-0.8.1.dist-info}/LICENSE +0 -0
- {xinference-0.7.5.dist-info → xinference-0.8.1.dist-info}/WHEEL +0 -0
- {xinference-0.7.5.dist-info → xinference-0.8.1.dist-info}/entry_points.txt +0 -0
- {xinference-0.7.5.dist-info → xinference-0.8.1.dist-info}/top_level.txt +0 -0
|
@@ -0,0 +1,48 @@
|
|
|
1
|
+
{
|
|
2
|
+
"name": "universal-cookie",
|
|
3
|
+
"version": "6.1.1",
|
|
4
|
+
"description": "Universal cookies for JavaScript",
|
|
5
|
+
"main": "cjs/index.js",
|
|
6
|
+
"module": "es6/index.js",
|
|
7
|
+
"types": "es6/index.d.ts",
|
|
8
|
+
"sideEffects": false,
|
|
9
|
+
"files": [
|
|
10
|
+
"lib",
|
|
11
|
+
"es6",
|
|
12
|
+
"cjs",
|
|
13
|
+
"umd",
|
|
14
|
+
"index.d.ts",
|
|
15
|
+
"LICENSE"
|
|
16
|
+
],
|
|
17
|
+
"repository": {
|
|
18
|
+
"type": "git",
|
|
19
|
+
"url": "https://github.com/bendotcodes/cookies.git"
|
|
20
|
+
},
|
|
21
|
+
"bugs": "https://github.com/bendotcodes/cookies/issues",
|
|
22
|
+
"homepage": "https://github.com/bendotcodes/cookies/tree/main/packages/universal-cookie#readme",
|
|
23
|
+
"keywords": [
|
|
24
|
+
"universal",
|
|
25
|
+
"isomophic",
|
|
26
|
+
"cookie"
|
|
27
|
+
],
|
|
28
|
+
"author": "Benoit Tremblay <me@ben.codes>",
|
|
29
|
+
"license": "MIT",
|
|
30
|
+
"scripts": {
|
|
31
|
+
"clean": "rimraf lib && rimraf es6 && rimraf cjs && rimraf umd",
|
|
32
|
+
"build": "npm run clean && npm run build-es6 && npm run build-cjs && npm run build-umd && npm run build-legacy",
|
|
33
|
+
"build-es6": "tsc",
|
|
34
|
+
"build-cjs": "babel es6 -D -d cjs",
|
|
35
|
+
"build-umd": "rollup -c",
|
|
36
|
+
"build-legacy": "babel es6 -D -d lib"
|
|
37
|
+
},
|
|
38
|
+
"dependencies": {
|
|
39
|
+
"@types/cookie": "^0.5.1",
|
|
40
|
+
"cookie": "^0.5.0"
|
|
41
|
+
},
|
|
42
|
+
"devDependencies": {
|
|
43
|
+
"@babel/cli": "^7.22.10",
|
|
44
|
+
"rimraf": "^3.0.2",
|
|
45
|
+
"rollup": "^3.28.1",
|
|
46
|
+
"typescript": "^5.2.2"
|
|
47
|
+
}
|
|
48
|
+
}
|
|
@@ -28,6 +28,7 @@
|
|
|
28
28
|
"@testing-library/user-event": "^13.5.0",
|
|
29
29
|
"formik": "^2.4.2",
|
|
30
30
|
"react": "^18.2.0",
|
|
31
|
+
"react-cookie": "^6.1.1",
|
|
31
32
|
"react-dom": "^18.2.0",
|
|
32
33
|
"react-pro-sidebar": "^1.1.0-alpha.1",
|
|
33
34
|
"react-router-dom": "^6.14.1",
|
|
@@ -4960,6 +4961,11 @@
|
|
|
4960
4961
|
"@types/node": "*"
|
|
4961
4962
|
}
|
|
4962
4963
|
},
|
|
4964
|
+
"node_modules/@types/cookie": {
|
|
4965
|
+
"version": "0.5.4",
|
|
4966
|
+
"resolved": "https://registry.npmjs.org/@types/cookie/-/cookie-0.5.4.tgz",
|
|
4967
|
+
"integrity": "sha512-7z/eR6O859gyWIAjuvBWFzNURmf2oPBmJlfVWkwehU5nzIyjwBsTh7WMmEEV4JFnHuQ3ex4oyTvfKzcyJVDBNA=="
|
|
4968
|
+
},
|
|
4963
4969
|
"node_modules/@types/d3-color": {
|
|
4964
4970
|
"version": "2.0.3",
|
|
4965
4971
|
"resolved": "https://registry.npmjs.org/@types/d3-color/-/d3-color-2.0.3.tgz",
|
|
@@ -5069,6 +5075,15 @@
|
|
|
5069
5075
|
"@types/node": "*"
|
|
5070
5076
|
}
|
|
5071
5077
|
},
|
|
5078
|
+
"node_modules/@types/hoist-non-react-statics": {
|
|
5079
|
+
"version": "3.3.5",
|
|
5080
|
+
"resolved": "https://registry.npmjs.org/@types/hoist-non-react-statics/-/hoist-non-react-statics-3.3.5.tgz",
|
|
5081
|
+
"integrity": "sha512-SbcrWzkKBw2cdwRTwQAswfpB9g9LJWfjtUeW/jvNwbhC8cpmmNYVePa+ncbUe0rGTQ7G3Ff6mYUN2VMfLVr+Sg==",
|
|
5082
|
+
"dependencies": {
|
|
5083
|
+
"@types/react": "*",
|
|
5084
|
+
"hoist-non-react-statics": "^3.3.0"
|
|
5085
|
+
}
|
|
5086
|
+
},
|
|
5072
5087
|
"node_modules/@types/html-minifier-terser": {
|
|
5073
5088
|
"version": "6.1.0",
|
|
5074
5089
|
"resolved": "https://registry.npmjs.org/@types/html-minifier-terser/-/html-minifier-terser-6.1.0.tgz",
|
|
@@ -15863,6 +15878,19 @@
|
|
|
15863
15878
|
"node": ">=14"
|
|
15864
15879
|
}
|
|
15865
15880
|
},
|
|
15881
|
+
"node_modules/react-cookie": {
|
|
15882
|
+
"version": "6.1.1",
|
|
15883
|
+
"resolved": "https://registry.npmjs.org/react-cookie/-/react-cookie-6.1.1.tgz",
|
|
15884
|
+
"integrity": "sha512-fuFRpf8LH6SfmVMowDUIRywJF5jAUDUWrm0EI5VdXfTl5bPcJ7B0zWbuYpT0Tvikx7Gs18MlvAT+P+744dUz2g==",
|
|
15885
|
+
"dependencies": {
|
|
15886
|
+
"@types/hoist-non-react-statics": "^3.3.1",
|
|
15887
|
+
"hoist-non-react-statics": "^3.3.2",
|
|
15888
|
+
"universal-cookie": "^6.0.0"
|
|
15889
|
+
},
|
|
15890
|
+
"peerDependencies": {
|
|
15891
|
+
"react": ">= 16.3.0"
|
|
15892
|
+
}
|
|
15893
|
+
},
|
|
15866
15894
|
"node_modules/react-dev-utils": {
|
|
15867
15895
|
"version": "12.0.1",
|
|
15868
15896
|
"resolved": "https://registry.npmjs.org/react-dev-utils/-/react-dev-utils-12.0.1.tgz",
|
|
@@ -18450,6 +18478,15 @@
|
|
|
18450
18478
|
"node": ">=8"
|
|
18451
18479
|
}
|
|
18452
18480
|
},
|
|
18481
|
+
"node_modules/universal-cookie": {
|
|
18482
|
+
"version": "6.1.1",
|
|
18483
|
+
"resolved": "https://registry.npmjs.org/universal-cookie/-/universal-cookie-6.1.1.tgz",
|
|
18484
|
+
"integrity": "sha512-33S9x3CpdUnnjwTNs2Fgc41WGve2tdLtvaK2kPSbZRc5pGpz2vQFbRWMxlATsxNNe/Cy8SzmnmbuBM85jpZPtA==",
|
|
18485
|
+
"dependencies": {
|
|
18486
|
+
"@types/cookie": "^0.5.1",
|
|
18487
|
+
"cookie": "^0.5.0"
|
|
18488
|
+
}
|
|
18489
|
+
},
|
|
18453
18490
|
"node_modules/universalify": {
|
|
18454
18491
|
"version": "2.0.0",
|
|
18455
18492
|
"resolved": "https://registry.npmjs.org/universalify/-/universalify-2.0.0.tgz",
|
xinference/web/ui/package.json
CHANGED
|
@@ -11,9 +11,9 @@
|
|
|
11
11
|
"@fullcalendar/list": "^6.1.8",
|
|
12
12
|
"@fullcalendar/timegrid": "^6.1.8",
|
|
13
13
|
"@mui/icons-material": "^5.14.0",
|
|
14
|
+
"@mui/lab": "latest",
|
|
14
15
|
"@mui/material": "^5.14.0",
|
|
15
16
|
"@mui/x-data-grid": "^6.10.0",
|
|
16
|
-
"@mui/lab": "latest",
|
|
17
17
|
"@nivo/bar": "^0.83.0",
|
|
18
18
|
"@nivo/core": "^0.83.0",
|
|
19
19
|
"@nivo/geo": "^0.83.0",
|
|
@@ -24,6 +24,7 @@
|
|
|
24
24
|
"@testing-library/user-event": "^13.5.0",
|
|
25
25
|
"formik": "^2.4.2",
|
|
26
26
|
"react": "^18.2.0",
|
|
27
|
+
"react-cookie": "^6.1.1",
|
|
27
28
|
"react-dom": "^18.2.0",
|
|
28
29
|
"react-pro-sidebar": "^1.1.0-alpha.1",
|
|
29
30
|
"react-router-dom": "^6.14.1",
|
|
@@ -58,9 +59,9 @@
|
|
|
58
59
|
]
|
|
59
60
|
},
|
|
60
61
|
"devDependencies": {
|
|
61
|
-
"@babel/plugin-proposal-private-property-in-object": "^7.21.11",
|
|
62
62
|
"@babel/core": "^7.21.0",
|
|
63
63
|
"@babel/eslint-parser": "^7.19.1",
|
|
64
|
+
"@babel/plugin-proposal-private-property-in-object": "^7.21.11",
|
|
64
65
|
"eslint": "^7.32.0",
|
|
65
66
|
"eslint-config-prettier": "^8.5.0",
|
|
66
67
|
"eslint-plugin-react": "^7.24.0",
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: xinference
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.8.1
|
|
4
4
|
Summary: Model Serving Made Easy
|
|
5
5
|
Home-page: https://github.com/xorbitsai/inference
|
|
6
6
|
Author: Qin Xuye
|
|
@@ -19,9 +19,10 @@ Classifier: Programming Language :: Python :: Implementation :: CPython
|
|
|
19
19
|
Classifier: Topic :: Software Development :: Libraries
|
|
20
20
|
Description-Content-Type: text/markdown
|
|
21
21
|
License-File: LICENSE
|
|
22
|
-
Requires-Dist: xoscar >=0.1
|
|
22
|
+
Requires-Dist: xoscar >=0.2.1
|
|
23
23
|
Requires-Dist: torch
|
|
24
24
|
Requires-Dist: gradio >=3.39.0
|
|
25
|
+
Requires-Dist: pillow
|
|
25
26
|
Requires-Dist: click
|
|
26
27
|
Requires-Dist: tqdm >=4.27
|
|
27
28
|
Requires-Dist: tabulate
|
|
@@ -36,6 +37,9 @@ Requires-Dist: s3fs
|
|
|
36
37
|
Requires-Dist: modelscope >=1.10.0
|
|
37
38
|
Requires-Dist: sse-starlette >=1.6.5
|
|
38
39
|
Requires-Dist: openai >1
|
|
40
|
+
Requires-Dist: python-jose[cryptography]
|
|
41
|
+
Requires-Dist: passlib[bcrypt]
|
|
42
|
+
Requires-Dist: aioprometheus[starlette]
|
|
39
43
|
Provides-Extra: all
|
|
40
44
|
Requires-Dist: chatglm-cpp >=0.3.0 ; extra == 'all'
|
|
41
45
|
Requires-Dist: ctransformers ; extra == 'all'
|
|
@@ -75,7 +79,6 @@ Requires-Dist: jieba >=0.42.0 ; extra == 'dev'
|
|
|
75
79
|
Requires-Dist: flake8 >=3.8.0 ; extra == 'dev'
|
|
76
80
|
Requires-Dist: black ; extra == 'dev'
|
|
77
81
|
Requires-Dist: openai >1 ; extra == 'dev'
|
|
78
|
-
Requires-Dist: pillow ; extra == 'dev'
|
|
79
82
|
Requires-Dist: opencv-python ; extra == 'dev'
|
|
80
83
|
Requires-Dist: langchain ; extra == 'dev'
|
|
81
84
|
Requires-Dist: orjson ; extra == 'dev'
|
|
@@ -140,19 +143,19 @@ potential of cutting-edge AI models.
|
|
|
140
143
|
|
|
141
144
|
## 🔥 Hot Topics
|
|
142
145
|
### Framework Enhancements
|
|
146
|
+
- Docker image: [#855](https://github.com/xorbitsai/inference/pull/855)
|
|
147
|
+
- Support multimodal: [#829](https://github.com/xorbitsai/inference/pull/829)
|
|
143
148
|
- Auto recover: [#694](https://github.com/xorbitsai/inference/pull/694)
|
|
144
149
|
- Function calling API: [#701](https://github.com/xorbitsai/inference/pull/701), here's example: https://github.com/xorbitsai/inference/blob/main/examples/FunctionCall.ipynb
|
|
145
150
|
- Support rerank model: [#672](https://github.com/xorbitsai/inference/pull/672)
|
|
146
151
|
- Speculative decoding: [#509](https://github.com/xorbitsai/inference/pull/509)
|
|
147
|
-
- Incorporate vLLM: [#445](https://github.com/xorbitsai/inference/pull/445)
|
|
148
152
|
### New Models
|
|
153
|
+
- Built-in support for [qwen-vl](https://huggingface.co/Qwen/Qwen-VL-Chat): [#829](https://github.com/xorbitsai/inference/pull/829)
|
|
149
154
|
- Built-in support for [phi-2](https://huggingface.co/microsoft/phi-2): [#828](https://github.com/xorbitsai/inference/pull/828)
|
|
150
155
|
- Built-in support for [mistral-instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2): [#796](https://github.com/xorbitsai/inference/pull/796)
|
|
151
156
|
- Built-in support for [deepseek-llm](https://huggingface.co/deepseek-ai) and [deepseek-coder](https://huggingface.co/deepseek-ai): [#786](https://github.com/xorbitsai/inference/pull/786)
|
|
152
157
|
- Built-in support for [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1): [#782](https://github.com/xorbitsai/inference/pull/782)
|
|
153
158
|
- Built-in support for [OpenHermes 2.5](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B): [#776](https://github.com/xorbitsai/inference/pull/776)
|
|
154
|
-
- Built-in support for [Yi](https://huggingface.co/01-ai): [#629](https://github.com/xorbitsai/inference/pull/629)
|
|
155
|
-
- Built-in support for [zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha) and [zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta): [#597](https://github.com/xorbitsai/inference/pull/597)
|
|
156
159
|
### Integrations
|
|
157
160
|
- [Dify](https://docs.dify.ai/advanced/model-configuration/xinference): an LLMOps platform that enables developers (and even non-developers) to quickly build useful applications based on large language models, ensuring they are visual, operable, and improvable.
|
|
158
161
|
- [Chatbox](https://chatboxai.app/): a desktop client for multiple cutting-edge LLM models, available on Windows, Mac and Linux.
|
|
@@ -207,6 +210,14 @@ with popular third-party libraries including [LangChain](https://python.langchai
|
|
|
207
210
|
|
|
208
211
|
The lightest way to experience Xinference is to try our [Juypter Notebook on Google Colab](https://colab.research.google.com/github/xorbitsai/inference/blob/main/examples/Xinference_Quick_Start.ipynb).
|
|
209
212
|
|
|
213
|
+
### Docker
|
|
214
|
+
|
|
215
|
+
Nvidia GPU users can start Xinference server using [Xinference Docker Image](https://inference.readthedocs.io/en/latest/getting_started/using_docker_image.html). Prior to executing the installation command, ensure that both [Docker](https://docs.docker.com/get-docker/) and [CUDA](https://developer.nvidia.com/cuda-downloads) are set up on your system.
|
|
216
|
+
|
|
217
|
+
```bash
|
|
218
|
+
docker run --name xinference -d -p 9997:9997 -e XINFERENCE_HOME=/data -v </on/your/host>:/data --gpus all xprobe/xinference:latest xinference-local -H 0.0.0.0
|
|
219
|
+
```
|
|
220
|
+
|
|
210
221
|
### Quick Start
|
|
211
222
|
|
|
212
223
|
Install Xinference by using pip as follows. (For more options, see [Installation page](https://inference.readthedocs.io/en/latest/getting_started/installation.html).)
|