xinference 1.5.0.post1__py3-none-any.whl → 1.5.1__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.

Files changed (89) hide show
  1. xinference/_version.py +3 -3
  2. xinference/api/restful_api.py +10 -3
  3. xinference/constants.py +5 -1
  4. xinference/core/supervisor.py +12 -3
  5. xinference/core/utils.py +1 -1
  6. xinference/core/worker.py +2 -2
  7. xinference/deploy/cmdline.py +17 -0
  8. xinference/model/audio/core.py +1 -1
  9. xinference/model/audio/model_spec.json +43 -43
  10. xinference/model/audio/model_spec_modelscope.json +13 -13
  11. xinference/model/llm/__init__.py +3 -5
  12. xinference/model/llm/core.py +14 -0
  13. xinference/model/llm/llama_cpp/core.py +15 -4
  14. xinference/model/llm/llm_family.json +3251 -4304
  15. xinference/model/llm/llm_family.py +62 -6
  16. xinference/model/llm/llm_family_csghub.json +0 -32
  17. xinference/model/llm/llm_family_modelscope.json +1161 -1789
  18. xinference/model/llm/llm_family_openmind_hub.json +19 -325
  19. xinference/model/llm/lmdeploy/core.py +7 -2
  20. xinference/model/llm/mlx/core.py +19 -6
  21. xinference/model/llm/sglang/core.py +25 -10
  22. xinference/model/llm/transformers/chatglm.py +8 -1
  23. xinference/model/llm/transformers/cogagent.py +10 -12
  24. xinference/model/llm/transformers/cogvlm2.py +6 -3
  25. xinference/model/llm/transformers/cogvlm2_video.py +3 -6
  26. xinference/model/llm/transformers/core.py +50 -58
  27. xinference/model/llm/transformers/deepseek_v2.py +4 -2
  28. xinference/model/llm/transformers/deepseek_vl.py +10 -4
  29. xinference/model/llm/transformers/deepseek_vl2.py +9 -4
  30. xinference/model/llm/transformers/gemma3.py +15 -7
  31. xinference/model/llm/transformers/glm4v.py +2 -20
  32. xinference/model/llm/transformers/glm_edge_v.py +3 -20
  33. xinference/model/llm/transformers/intern_vl.py +3 -6
  34. xinference/model/llm/transformers/internlm2.py +1 -1
  35. xinference/model/llm/transformers/minicpmv25.py +4 -2
  36. xinference/model/llm/transformers/minicpmv26.py +5 -3
  37. xinference/model/llm/transformers/omnilmm.py +1 -1
  38. xinference/model/llm/transformers/opt.py +1 -1
  39. xinference/model/llm/transformers/ovis2.py +302 -0
  40. xinference/model/llm/transformers/qwen-omni.py +2 -1
  41. xinference/model/llm/transformers/qwen2_audio.py +3 -1
  42. xinference/model/llm/transformers/qwen2_vl.py +5 -1
  43. xinference/model/llm/transformers/qwen_vl.py +5 -2
  44. xinference/model/llm/utils.py +28 -0
  45. xinference/model/llm/vllm/core.py +73 -9
  46. xinference/model/llm/vllm/distributed_executor.py +8 -7
  47. xinference/model/llm/vllm/xavier/allocator.py +1 -1
  48. xinference/model/llm/vllm/xavier/block_manager.py +1 -1
  49. xinference/model/llm/vllm/xavier/block_tracker.py +3 -3
  50. xinference/model/llm/vllm/xavier/executor.py +1 -1
  51. xinference/model/llm/vllm/xavier/test/test_xavier.py +1 -1
  52. xinference/model/video/diffusers.py +30 -3
  53. xinference/model/video/model_spec.json +46 -0
  54. xinference/model/video/model_spec_modelscope.json +48 -0
  55. xinference/types.py +2 -0
  56. xinference/web/ui/build/asset-manifest.json +6 -6
  57. xinference/web/ui/build/index.html +1 -1
  58. xinference/web/ui/build/static/css/{main.0f6523be.css → main.337afe76.css} +2 -2
  59. xinference/web/ui/build/static/css/main.337afe76.css.map +1 -0
  60. xinference/web/ui/build/static/js/main.91e77b5c.js +3 -0
  61. xinference/web/ui/build/static/js/main.91e77b5c.js.map +1 -0
  62. xinference/web/ui/node_modules/.cache/babel-loader/5c08e2cd07809ed3e41486b16652253404cbb63a3ff8d0366ee50f57e2413cea.json +1 -0
  63. xinference/web/ui/node_modules/.cache/babel-loader/5e6edb0fb87e3798f142e9abf8dd2dc46bab33a60d31dff525797c0c99887097.json +1 -0
  64. xinference/web/ui/node_modules/.cache/babel-loader/6087820be1bd5c02c42dff797e7df365448ef35ab26dd5d6bd33e967e05cbfd4.json +1 -0
  65. xinference/web/ui/node_modules/.cache/babel-loader/6798e126f3bc5f95a4c16a9c2ad52ffe77970c62406d83e20604dfda7ffd2247.json +1 -0
  66. xinference/web/ui/node_modules/.cache/babel-loader/b617f7d21a95045fc57b26a9373551740f1978a826134cbf705c3a1bf8714a93.json +1 -0
  67. xinference/web/ui/node_modules/.cache/babel-loader/c1506cb142151366074975f30fa1ff9cd6e5e978b62a4b074dfc16fe08d70d75.json +1 -0
  68. xinference/web/ui/node_modules/.cache/babel-loader/c5c7c2cd1b863ce41adff2c4737bba06eef3a1acf28288cb83d992060f6b8923.json +1 -0
  69. xinference/web/ui/src/locales/en.json +1 -0
  70. xinference/web/ui/src/locales/zh.json +1 -0
  71. {xinference-1.5.0.post1.dist-info → xinference-1.5.1.dist-info}/METADATA +1 -1
  72. {xinference-1.5.0.post1.dist-info → xinference-1.5.1.dist-info}/RECORD +77 -78
  73. {xinference-1.5.0.post1.dist-info → xinference-1.5.1.dist-info}/WHEEL +1 -1
  74. xinference/model/llm/transformers/compression.py +0 -258
  75. xinference/model/llm/transformers/yi_vl.py +0 -239
  76. xinference/web/ui/build/static/css/main.0f6523be.css.map +0 -1
  77. xinference/web/ui/build/static/js/main.58bd483c.js +0 -3
  78. xinference/web/ui/build/static/js/main.58bd483c.js.map +0 -1
  79. xinference/web/ui/node_modules/.cache/babel-loader/51709f5d3e53bcf19e613662ef9b91fb9174942c5518987a248348dd4e1e0e02.json +0 -1
  80. xinference/web/ui/node_modules/.cache/babel-loader/69081049f0c7447544b7cfd73dd13d8846c02fe5febe4d81587e95c89a412d5b.json +0 -1
  81. xinference/web/ui/node_modules/.cache/babel-loader/8f9af2979e45d4648f0cfae108363e58ee421c29a9d4e7329b6f06d9adfd4133.json +0 -1
  82. xinference/web/ui/node_modules/.cache/babel-loader/9c8b1a86e7c65b2b2599a205e30920652d6c2105f926508ef5bcf29a3ef4ce76.json +0 -1
  83. xinference/web/ui/node_modules/.cache/babel-loader/b8551e9775a01b28ae674125c688febe763732ea969ae344512e64ea01bf632e.json +0 -1
  84. xinference/web/ui/node_modules/.cache/babel-loader/efe7cd132c27a8f9fd5352a394c491fd5fb0da0348cf9fcbd923164a32365eab.json +0 -1
  85. xinference/web/ui/node_modules/.cache/babel-loader/f199e8173f6409a5802ed44acb95f218388131136504b2e9132129e150c92f9a.json +0 -1
  86. /xinference/web/ui/build/static/js/{main.58bd483c.js.LICENSE.txt → main.91e77b5c.js.LICENSE.txt} +0 -0
  87. {xinference-1.5.0.post1.dist-info → xinference-1.5.1.dist-info}/entry_points.txt +0 -0
  88. {xinference-1.5.0.post1.dist-info → xinference-1.5.1.dist-info}/licenses/LICENSE +0 -0
  89. {xinference-1.5.0.post1.dist-info → xinference-1.5.1.dist-info}/top_level.txt +0 -0
@@ -1 +0,0 @@
1
- {"ast":null,"code":"export var llmAllDataKey=['model_uid','model_name','model_type','model_engine','model_format','model_size_in_billions','quantization','n_worker','n_gpu','n_gpu_layers','replica','request_limits','worker_ip','gpu_idx','download_hub','model_path','reasoning_content','gguf_quantization','gguf_model_path','cpu_offload','peft_model_config'];export var additionalParameterTipList={'transformers':['torch_dtype','device'],'llama.cpp':['n_ctx','use_mmap','use_mlock'],'vllm':['block_size','gpu_memory_utilization','max_num_seqs','max_model_len','guided_decoding_backend','scheduling_policy','tensor_parallel_size','pipeline_parallel_size','enable_prefix_caching','enable_chunked_prefill','enforce_eager','cpu_offload_gb','disable_custom_all_reduce','limit_mm_per_prompt','model_quantization','mm_processor_kwargs','min_pixels','max_pixels'],'sglang':['mem_fraction_static','attention_reduce_in_fp32','tp_size','dp_size','chunked_prefill_size','cpu_offload_gb','enable_dp_attention','enable_ep_moe'],'mlx':['cache_limit_gb','max_kv_size']};export var featureModels=[{type:'llm',feature_models:['deepseek-v3','deepseek-r1','deepseek-r1-distill-qwen','deepseek-r1-distill-llama','qwen2.5-instruct','qwen2.5-vl-instruct','qwen2.5-coder-instruct','QwQ-32B','llama-3.1-instruct','gemma-3-it']},{type:'embedding',feature_models:['bge-large-zh-v1.5','bge-large-en-v1.5','bge-m3','gte-Qwen2','jina-embeddings-v3']},{type:'rerank',feature_models:[]},{type:'image',feature_models:['FLUX.1-dev','FLUX.1-schnell','sd3.5-large','HunyuanDiT-v1.2','sd3.5-medium']},{type:'audio',feature_models:['CosyVoice2-0.5B','FishSpeech-1.5','F5-TTS','ChatTTS','SenseVoiceSmall','whisper-large-v3']},{type:'video',feature_models:[]}];","map":{"version":3,"names":["llmAllDataKey","additionalParameterTipList","featureModels","type","feature_models"],"sources":["/home/runner/work/inference/inference/xinference/web/ui/src/scenes/launch_model/data/data.js"],"sourcesContent":["export const llmAllDataKey = [\n 'model_uid',\n 'model_name',\n 'model_type',\n 'model_engine',\n 'model_format',\n 'model_size_in_billions',\n 'quantization',\n 'n_worker',\n 'n_gpu',\n 'n_gpu_layers',\n 'replica',\n 'request_limits',\n 'worker_ip',\n 'gpu_idx',\n 'download_hub',\n 'model_path',\n 'reasoning_content',\n 'gguf_quantization',\n 'gguf_model_path',\n 'cpu_offload',\n 'peft_model_config',\n]\n\nexport const additionalParameterTipList = {\n 'transformers': ['torch_dtype', 'device'],\n 'llama.cpp': ['n_ctx', 'use_mmap', 'use_mlock'],\n 'vllm': [\n 'block_size',\n 'gpu_memory_utilization',\n 'max_num_seqs',\n 'max_model_len',\n 'guided_decoding_backend',\n 'scheduling_policy',\n 'tensor_parallel_size',\n 'pipeline_parallel_size',\n 'enable_prefix_caching',\n 'enable_chunked_prefill',\n 'enforce_eager',\n 'cpu_offload_gb',\n 'disable_custom_all_reduce',\n 'limit_mm_per_prompt',\n 'model_quantization',\n 'mm_processor_kwargs',\n 'min_pixels',\n 'max_pixels',\n ],\n 'sglang': [\n 'mem_fraction_static',\n 'attention_reduce_in_fp32',\n 'tp_size',\n 'dp_size',\n 'chunked_prefill_size',\n 'cpu_offload_gb',\n 'enable_dp_attention',\n 'enable_ep_moe',\n ],\n 'mlx': ['cache_limit_gb', 'max_kv_size'],\n}\n\nexport const featureModels = [\n {\n type: 'llm',\n feature_models: [\n 'deepseek-v3',\n 'deepseek-r1',\n 'deepseek-r1-distill-qwen',\n 'deepseek-r1-distill-llama',\n 'qwen2.5-instruct',\n 'qwen2.5-vl-instruct',\n 'qwen2.5-coder-instruct',\n 'QwQ-32B',\n 'llama-3.1-instruct',\n 'gemma-3-it',\n ],\n },\n {\n type: 'embedding',\n feature_models: [\n 'bge-large-zh-v1.5',\n 'bge-large-en-v1.5',\n 'bge-m3',\n 'gte-Qwen2',\n 'jina-embeddings-v3',\n ],\n },\n {\n type: 'rerank',\n feature_models: [],\n },\n {\n type: 'image',\n feature_models: [\n 'FLUX.1-dev',\n 'FLUX.1-schnell',\n 'sd3.5-large',\n 'HunyuanDiT-v1.2',\n 'sd3.5-medium',\n ],\n },\n {\n type: 'audio',\n feature_models: [\n 'CosyVoice2-0.5B',\n 'FishSpeech-1.5',\n 'F5-TTS',\n 'ChatTTS',\n 'SenseVoiceSmall',\n 'whisper-large-v3',\n ],\n },\n {\n type: 'video',\n feature_models: [],\n },\n]\n"],"mappings":"AAAA,MAAO,IAAM,CAAAA,aAAa,CAAG,CAC3B,WAAW,CACX,YAAY,CACZ,YAAY,CACZ,cAAc,CACd,cAAc,CACd,wBAAwB,CACxB,cAAc,CACd,UAAU,CACV,OAAO,CACP,cAAc,CACd,SAAS,CACT,gBAAgB,CAChB,WAAW,CACX,SAAS,CACT,cAAc,CACd,YAAY,CACZ,mBAAmB,CACnB,mBAAmB,CACnB,iBAAiB,CACjB,aAAa,CACb,mBAAmB,CACpB,CAED,MAAO,IAAM,CAAAC,0BAA0B,CAAG,CACxC,cAAc,CAAE,CAAC,aAAa,CAAE,QAAQ,CAAC,CACzC,WAAW,CAAE,CAAC,OAAO,CAAE,UAAU,CAAE,WAAW,CAAC,CAC/C,MAAM,CAAE,CACN,YAAY,CACZ,wBAAwB,CACxB,cAAc,CACd,eAAe,CACf,yBAAyB,CACzB,mBAAmB,CACnB,sBAAsB,CACtB,wBAAwB,CACxB,uBAAuB,CACvB,wBAAwB,CACxB,eAAe,CACf,gBAAgB,CAChB,2BAA2B,CAC3B,qBAAqB,CACrB,oBAAoB,CACpB,qBAAqB,CACrB,YAAY,CACZ,YAAY,CACb,CACD,QAAQ,CAAE,CACR,qBAAqB,CACrB,0BAA0B,CAC1B,SAAS,CACT,SAAS,CACT,sBAAsB,CACtB,gBAAgB,CAChB,qBAAqB,CACrB,eAAe,CAChB,CACD,KAAK,CAAE,CAAC,gBAAgB,CAAE,aAAa,CACzC,CAAC,CAED,MAAO,IAAM,CAAAC,aAAa,CAAG,CAC3B,CACEC,IAAI,CAAE,KAAK,CACXC,cAAc,CAAE,CACd,aAAa,CACb,aAAa,CACb,0BAA0B,CAC1B,2BAA2B,CAC3B,kBAAkB,CAClB,qBAAqB,CACrB,wBAAwB,CACxB,SAAS,CACT,oBAAoB,CACpB,YAAY,CAEhB,CAAC,CACD,CACED,IAAI,CAAE,WAAW,CACjBC,cAAc,CAAE,CACd,mBAAmB,CACnB,mBAAmB,CACnB,QAAQ,CACR,WAAW,CACX,oBAAoB,CAExB,CAAC,CACD,CACED,IAAI,CAAE,QAAQ,CACdC,cAAc,CAAE,EAClB,CAAC,CACD,CACED,IAAI,CAAE,OAAO,CACbC,cAAc,CAAE,CACd,YAAY,CACZ,gBAAgB,CAChB,aAAa,CACb,iBAAiB,CACjB,cAAc,CAElB,CAAC,CACD,CACED,IAAI,CAAE,OAAO,CACbC,cAAc,CAAE,CACd,iBAAiB,CACjB,gBAAgB,CAChB,QAAQ,CACR,SAAS,CACT,iBAAiB,CACjB,kBAAkB,CAEtB,CAAC,CACD,CACED,IAAI,CAAE,OAAO,CACbC,cAAc,CAAE,EAClB,CAAC,CACF","ignoreList":[]},"metadata":{},"sourceType":"module","externalDependencies":[]}