xinference 0.11.0__py3-none-any.whl → 0.11.2__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 +30 -0
- xinference/client/restful/restful_client.py +29 -0
- xinference/core/cache_tracker.py +12 -1
- xinference/core/chat_interface.py +10 -4
- xinference/core/model.py +2 -2
- xinference/core/supervisor.py +30 -2
- xinference/core/utils.py +12 -0
- xinference/core/worker.py +4 -1
- xinference/deploy/cmdline.py +126 -0
- xinference/deploy/test/test_cmdline.py +24 -0
- xinference/fields.py +3 -1
- xinference/model/llm/__init__.py +2 -0
- xinference/model/llm/ggml/chatglm.py +98 -13
- xinference/model/llm/ggml/llamacpp.py +49 -2
- xinference/model/llm/llm_family.json +633 -9
- xinference/model/llm/llm_family.py +84 -10
- xinference/model/llm/llm_family_modelscope.json +337 -10
- xinference/model/llm/memory.py +332 -0
- xinference/model/llm/pytorch/chatglm.py +48 -0
- xinference/model/llm/pytorch/core.py +25 -6
- xinference/model/llm/pytorch/deepseek_vl.py +35 -9
- xinference/model/llm/pytorch/intern_vl.py +387 -0
- xinference/model/llm/pytorch/internlm2.py +32 -1
- xinference/model/llm/pytorch/qwen_vl.py +38 -11
- xinference/model/llm/pytorch/utils.py +38 -1
- xinference/model/llm/pytorch/yi_vl.py +42 -14
- xinference/model/llm/sglang/core.py +31 -9
- xinference/model/llm/utils.py +38 -5
- xinference/model/llm/vllm/core.py +87 -5
- xinference/model/rerank/core.py +23 -1
- xinference/model/utils.py +17 -7
- xinference/thirdparty/deepseek_vl/models/processing_vlm.py +1 -1
- xinference/thirdparty/deepseek_vl/models/siglip_vit.py +2 -2
- xinference/thirdparty/llava/mm_utils.py +3 -2
- xinference/thirdparty/llava/model/llava_arch.py +1 -1
- xinference/thirdparty/omnilmm/chat.py +6 -5
- xinference/types.py +10 -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.8e44da4b.js → main.551aa479.js} +3 -3
- xinference/web/ui/build/static/js/main.551aa479.js.map +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/1fa824d82b2af519de7700c594e50bde4bbca60d13bd3fabff576802e4070304.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/23caf6f1e52c43e983ca3bfd4189f41dbd645fa78f2dfdcd7f6b69bc41678665.json +1 -0
- xinference/web/ui/node_modules/.cache/babel-loader/a6da6bc3d0d2191adebee87fb58ecebe82d071087bd2f7f3a9c7fdd2ada130f2.json +1 -0
- {xinference-0.11.0.dist-info → xinference-0.11.2.dist-info}/METADATA +10 -8
- {xinference-0.11.0.dist-info → xinference-0.11.2.dist-info}/RECORD +52 -50
- xinference/web/ui/build/static/js/main.8e44da4b.js.map +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/1870cd6f7054d04e049e363c0a85526584fe25519378609d2838e28d7492bbf1.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/5393569d846332075b93b55656716a34f50e0a8c970be789502d7e6c49755fd7.json +0 -1
- xinference/web/ui/node_modules/.cache/babel-loader/ddaec68b88e5eff792df1e39a4b4b8b737bfc832293c015660c3c69334e3cf5c.json +0 -1
- /xinference/web/ui/build/static/js/{main.8e44da4b.js.LICENSE.txt → main.551aa479.js.LICENSE.txt} +0 -0
- {xinference-0.11.0.dist-info → xinference-0.11.2.dist-info}/LICENSE +0 -0
- {xinference-0.11.0.dist-info → xinference-0.11.2.dist-info}/WHEEL +0 -0
- {xinference-0.11.0.dist-info → xinference-0.11.2.dist-info}/entry_points.txt +0 -0
- {xinference-0.11.0.dist-info → xinference-0.11.2.dist-info}/top_level.txt +0 -0
xinference/types.py
CHANGED
|
@@ -187,6 +187,8 @@ class ChatglmCppGenerateConfig(TypedDict, total=False):
|
|
|
187
187
|
top_p: float
|
|
188
188
|
temperature: float
|
|
189
189
|
stream: bool
|
|
190
|
+
lora_name: Optional[str]
|
|
191
|
+
stream_options: Optional[Union[dict, None]]
|
|
190
192
|
|
|
191
193
|
|
|
192
194
|
class QWenCppModelConfig(TypedDict, total=False):
|
|
@@ -231,6 +233,7 @@ class LlamaCppGenerateConfig(TypedDict, total=False):
|
|
|
231
233
|
repetition_penalty: float
|
|
232
234
|
top_k: int
|
|
233
235
|
stream: bool
|
|
236
|
+
stream_options: Optional[Union[dict, None]]
|
|
234
237
|
tfs_z: float
|
|
235
238
|
mirostat_mode: int
|
|
236
239
|
mirostat_tau: float
|
|
@@ -279,6 +282,8 @@ class PytorchGenerateConfig(TypedDict, total=False):
|
|
|
279
282
|
stream_interval: int
|
|
280
283
|
model: Optional[str]
|
|
281
284
|
tools: Optional[List[Dict]]
|
|
285
|
+
lora_name: Optional[str]
|
|
286
|
+
stream_options: Optional[Union[dict, None]]
|
|
282
287
|
|
|
283
288
|
|
|
284
289
|
class PytorchModelConfig(TypedDict, total=False):
|
|
@@ -350,10 +355,12 @@ class CreateCompletionTorch(BaseModel):
|
|
|
350
355
|
stop: Optional[Union[str, List[str]]] = stop_field
|
|
351
356
|
stop_token_ids: Optional[Union[int, List[int]]] = none_field
|
|
352
357
|
stream: bool = stream_field
|
|
358
|
+
stream_options: Optional[Union[dict, None]] = stream_option_field
|
|
353
359
|
stream_interval: int = stream_interval_field
|
|
354
360
|
temperature: float = temperature_field
|
|
355
361
|
top_p: float = top_p_field
|
|
356
362
|
top_k: int = top_k_field
|
|
363
|
+
lora_name: Optional[str]
|
|
357
364
|
|
|
358
365
|
|
|
359
366
|
CreateCompletionLlamaCpp: BaseModel
|
|
@@ -366,6 +373,8 @@ try:
|
|
|
366
373
|
include_fields={
|
|
367
374
|
"grammar": (Optional[Any], None),
|
|
368
375
|
"max_tokens": (Optional[int], max_tokens_field),
|
|
376
|
+
"lora_name": (Optional[str], None),
|
|
377
|
+
"stream_options": (Optional[Union[dict, None]], None),
|
|
369
378
|
},
|
|
370
379
|
)
|
|
371
380
|
except ImportError:
|
|
@@ -393,7 +402,7 @@ class _CreateCompletionOpenAIFallback(BaseModel):
|
|
|
393
402
|
seed: Optional[int] = none_field
|
|
394
403
|
stop: Optional[Union[str, List[str]]] = stop_field
|
|
395
404
|
stream: bool = stream_field
|
|
396
|
-
stream_options: Optional[dict] = stream_option_field
|
|
405
|
+
stream_options: Optional[Union[dict, None]] = stream_option_field
|
|
397
406
|
suffix: Optional[str] = none_field
|
|
398
407
|
temperature: float = temperature_field
|
|
399
408
|
top_p: float = top_p_field
|
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
{
|
|
2
2
|
"files": {
|
|
3
3
|
"main.css": "./static/css/main.54bca460.css",
|
|
4
|
-
"main.js": "./static/js/main.
|
|
4
|
+
"main.js": "./static/js/main.551aa479.js",
|
|
5
5
|
"static/media/icon.webp": "./static/media/icon.4603d52c63041e5dfbfd.webp",
|
|
6
6
|
"index.html": "./index.html",
|
|
7
7
|
"main.54bca460.css.map": "./static/css/main.54bca460.css.map",
|
|
8
|
-
"main.
|
|
8
|
+
"main.551aa479.js.map": "./static/js/main.551aa479.js.map"
|
|
9
9
|
},
|
|
10
10
|
"entrypoints": [
|
|
11
11
|
"static/css/main.54bca460.css",
|
|
12
|
-
"static/js/main.
|
|
12
|
+
"static/js/main.551aa479.js"
|
|
13
13
|
]
|
|
14
14
|
}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
<!doctype html><html lang="en"><head><meta charset="utf-8"/><link rel="icon" href="./favicon.svg"/><meta name="viewport" content="width=device-width,initial-scale=1"/><meta name="theme-color" content="#000000"/><meta name="description" content="Web site created using create-react-app"/><link rel="apple-touch-icon" href="./logo192.png"/><link rel="manifest" href="./manifest.json"/><title>Xinference</title><script defer="defer" src="./static/js/main.
|
|
1
|
+
<!doctype html><html lang="en"><head><meta charset="utf-8"/><link rel="icon" href="./favicon.svg"/><meta name="viewport" content="width=device-width,initial-scale=1"/><meta name="theme-color" content="#000000"/><meta name="description" content="Web site created using create-react-app"/><link rel="apple-touch-icon" href="./logo192.png"/><link rel="manifest" href="./manifest.json"/><title>Xinference</title><script defer="defer" src="./static/js/main.551aa479.js"></script><link href="./static/css/main.54bca460.css" rel="stylesheet"></head><body><noscript>You need to enable JavaScript to run this app.</noscript><div id="root"></div></body></html>
|