xinference 0.14.1__py3-none-any.whl → 0.14.2__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/restful_api.py +15 -34
- xinference/client/restful/restful_client.py +2 -2
- xinference/core/chat_interface.py +44 -9
- xinference/core/model.py +4 -4
- xinference/core/scheduler.py +1 -2
- xinference/core/worker.py +1 -1
- xinference/deploy/cmdline.py +2 -2
- xinference/deploy/test/test_cmdline.py +7 -7
- xinference/model/llm/__init__.py +20 -27
- xinference/model/llm/{ggml/llamacpp.py → llama_cpp/core.py} +2 -35
- xinference/model/llm/llm_family.json +448 -1153
- xinference/model/llm/llm_family.py +14 -139
- xinference/model/llm/llm_family_modelscope.json +230 -313
- xinference/model/llm/memory.py +9 -9
- xinference/model/llm/sglang/core.py +2 -2
- xinference/model/llm/{pytorch → transformers}/chatglm.py +6 -13
- xinference/model/llm/{pytorch → transformers}/core.py +2 -10
- xinference/model/llm/transformers/intern_vl.py +457 -0
- xinference/model/llm/{pytorch → transformers}/internlm2.py +4 -8
- xinference/model/llm/{pytorch → transformers}/minicpmv26.py +67 -22
- xinference/model/llm/{pytorch → transformers}/utils.py +1 -2
- xinference/model/llm/utils.py +76 -70
- xinference/model/llm/vllm/core.py +110 -11
- xinference/model/utils.py +1 -95
- xinference/thirdparty/internvl/__init__.py +0 -0
- xinference/thirdparty/internvl/conversation.py +393 -0
- xinference/thirdparty/omnilmm/model/utils.py +16 -1
- xinference/web/ui/build/asset-manifest.json +3 -3
- xinference/web/ui/build/index.html +1 -1
- xinference/web/ui/build/static/js/main.ffc26121.js +3 -0
- xinference/web/ui/build/static/js/main.ffc26121.js.map +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/213b5913e164773c2b0567455377765715f5f07225fbac77ad8e1e9dc9648a47.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/4de9a6942c5f1749d6cbfdd54279699975f16016b182848bc253886f52ec2ec3.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/5391543180fead1eeef5364300301498d58a7d91d62de3841a32768b67f4552f.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/5c26a23b5eacf5b752a08531577ae3840bb247745ef9a39583dc2d05ba93a82a.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/714c37ce0ec5b5c591033f02be2f3f491fdd70da3ef568ee4a4f94689a3d5ca2.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/822586ed1077201b64b954f12f25e3f9b45678c1acbabe53d8af3ca82ca71f33.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/978b57d1a04a701bc3fcfebc511f5f274eed6ed7eade67f6fb76c27d5fd9ecc8.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/a797831de0dc74897f4b50b3426555d748f328b4c2cc391de709eadaf6a5f3e3.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/bd6ad8159341315a1764c397621a560809f7eb7219ab5174c801fca7e969d943.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/e64b7e8cedcf43d4c95deba60ec1341855c887705805bb62431693118b870c69.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/e91938976f229ce986b2907e51e1f00540b584ced0a315d498c172d13220739d.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/f72f011744c4649fabddca6f7a9327861ac0a315a89b1a2e62a39774e7863845.json +1 -0
- {xinference-0.14.1.dist-info → xinference-0.14.2.dist-info}/METADATA +12 -15
- {xinference-0.14.1.dist-info → xinference-0.14.2.dist-info}/RECORD +63 -70
- xinference/locale/utils.py +0 -39
- xinference/locale/zh_CN.json +0 -26
- xinference/model/llm/ggml/tools/__init__.py +0 -15
- xinference/model/llm/ggml/tools/convert_ggml_to_gguf.py +0 -498
- xinference/model/llm/ggml/tools/gguf.py +0 -884
- xinference/model/llm/pytorch/__init__.py +0 -13
- xinference/model/llm/pytorch/baichuan.py +0 -81
- xinference/model/llm/pytorch/falcon.py +0 -138
- xinference/model/llm/pytorch/intern_vl.py +0 -352
- xinference/model/llm/pytorch/vicuna.py +0 -69
- xinference/web/ui/build/static/js/main.17ca0398.js +0 -3
- xinference/web/ui/build/static/js/main.17ca0398.js.map +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/1444c41a4d04494f1cbc2d8c1537df107b451cb569cb2c1fbf5159f3a4841a5f.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/44774c783428f952d8e2e4ad0998a9c5bc16a57cd9c68b7c5ff18aaa5a41d65c.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/5262556baf9207738bf6a8ba141ec6599d0a636345c245d61fdf88d3171998cb.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/6450605fac003812485f6251b9f0caafbf2e5bfc3bbe2f000050d9e2fdb8dcd3.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/71684495d995c7e266eecc6a0ad8ea0284cc785f80abddf863789c57a6134969.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/80acd1edf31542ab1dcccfad02cb4b38f3325cff847a781fcce97500cfd6f878.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/8a9742ddd8ba8546ef42dc14caca443f2b4524fabed7bf269e0eff3b7b64ee7d.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/d06a96a3c9c32e42689094aa3aaad41c8125894e956b8f84a70fadce6e3f65b3.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/d93730e2b5d7e8c957b4d0965d2ed1dac9045a649adbd47c220d11f255d4b1e0.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/e656dc00b4d8b387f0a81ba8fc558767df1601c66369e2eb86a5ef27cf080572.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/f28b83886159d83b84f099b05d607a822dca4dd7f2d8aa6d56fe08bab0b5b086.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/f3e02274cb1964e99b1fe69cbb6db233d3d8d7dd05d50ebcdb8e66d50b224b7b.json +0 -1
- /xinference/{locale → model/llm/llama_cpp}/__init__.py +0 -0
- /xinference/model/llm/{ggml → transformers}/__init__.py +0 -0
- /xinference/model/llm/{pytorch → transformers}/cogvlm2.py +0 -0
- /xinference/model/llm/{pytorch → transformers}/compression.py +0 -0
- /xinference/model/llm/{pytorch → transformers}/deepseek_vl.py +0 -0
- /xinference/model/llm/{pytorch → transformers}/glm4v.py +0 -0
- /xinference/model/llm/{pytorch → transformers}/llama_2.py +0 -0
- /xinference/model/llm/{pytorch → transformers}/minicpmv25.py +0 -0
- /xinference/model/llm/{pytorch → transformers}/omnilmm.py +0 -0
- /xinference/model/llm/{pytorch → transformers}/qwen_vl.py +0 -0
- /xinference/model/llm/{pytorch → transformers}/tensorizer_utils.py +0 -0
- /xinference/model/llm/{pytorch → transformers}/yi_vl.py +0 -0
- /xinference/web/ui/build/static/js/{main.17ca0398.js.LICENSE.txt → main.ffc26121.js.LICENSE.txt} +0 -0
- {xinference-0.14.1.dist-info → xinference-0.14.2.dist-info}/LICENSE +0 -0
- {xinference-0.14.1.dist-info → xinference-0.14.2.dist-info}/WHEEL +0 -0
- {xinference-0.14.1.dist-info → xinference-0.14.2.dist-info}/entry_points.txt +0 -0
- {xinference-0.14.1.dist-info → xinference-0.14.2.dist-info}/top_level.txt +0 -0
There are too many changes on this page to be displayed.
The amount of changes on this page would crash your brower.
You can still verify the content by downloading the package file manually.