xinference 1.5.1__py3-none-any.whl → 1.6.0.post1__py3-none-any.whl

xinference/thirdparty/matcha/hifigan/xutils.py

@@ -3,12 +3,12 @@
 import glob
 import os
 
-import matplotlib
+# import matplotlib
 import torch
 from torch.nn.utils import weight_norm
 
-matplotlib.use("Agg")
-import matplotlib.pylab as plt
+# matplotlib.use("Agg")
+# import matplotlib.pylab as plt
 
 
 def plot_spectrogram(spectrogram):

xinference/types.py

@@ -247,56 +247,6 @@ class LogitsProcessorList(List[LogitsProcessor]):
         return scores
 
 
-class LlamaCppGenerateConfig(TypedDict, total=False):
-    suffix: Optional[str]
-    max_tokens: int
-    temperature: float
-    top_p: float
-    logprobs: Optional[int]
-    echo: bool
-    stop: Optional[Union[str, List[str]]]
-    frequency_penalty: float
-    presence_penalty: float
-    repetition_penalty: float
-    top_k: int
-    stream: bool
-    stream_options: Optional[Union[dict, None]]
-    tfs_z: float
-    mirostat_mode: int
-    mirostat_tau: float
-    mirostat_eta: float
-    model: Optional[str]
-    grammar: Optional[Any]
-    stopping_criteria: Optional["StoppingCriteriaList"]
-    logits_processor: Optional["LogitsProcessorList"]
-    tools: Optional[List[Dict]]
-
-
-class LlamaCppModelConfig(TypedDict, total=False):
-    n_ctx: int
-    n_parts: int
-    n_gpu_layers: int
-    split_mode: int
-    main_gpu: int
-    seed: int
-    f16_kv: bool
-    logits_all: bool
-    vocab_only: bool
-    use_mmap: bool
-    use_mlock: bool
-    n_threads: Optional[int]
-    n_parallel: Optional[int]
-    n_batch: int
-    last_n_tokens_size: int
-    lora_base: Optional[str]
-    lora_path: Optional[str]
-    low_vram: bool
-    n_gqa: Optional[int]  # (TEMPORARY) must be 8 for llama2 70b
-    rms_norm_eps: Optional[float]  # (TEMPORARY)
-    verbose: bool
-    reasoning_content: bool
-
-
 class PytorchGenerateConfig(TypedDict, total=False):
     temperature: float
     repetition_penalty: float
@@ -415,24 +365,6 @@ class CreateCompletionTorch(BaseModel):
     chat_template_kwargs: Optional[Union[str, Dict[str, Any]]]
 
 
-CreateCompletionLlamaCpp: BaseModel
-try:
-    from llama_cpp import Llama
-
-    CreateCompletionLlamaCpp = get_pydantic_model_from_method(
-        Llama.create_completion,
-        exclude_fields=["model", "prompt", "grammar", "max_tokens"],
-        include_fields={
-            "grammar": (Optional[Any], None),
-            "max_tokens": (Optional[int], max_tokens_field),
-            "lora_name": (Optional[str], None),
-            "stream_options": (Optional[Union[dict, None]], None),
-        },
-    )
-except ImportError:
-    CreateCompletionLlamaCpp = create_model("CreateCompletionLlamaCpp")
-
-
 # This type is for openai API compatibility
 CreateCompletionOpenAI: BaseModel
 
@@ -448,7 +380,6 @@ CreateCompletionOpenAI = fix_forward_ref(CreateCompletionOpenAI)
 class CreateCompletion(
     ModelAndPrompt,
     CreateCompletionTorch,
-    CreateCompletionLlamaCpp,
     CreateCompletionOpenAI,
 ):
     pass
@@ -460,7 +391,6 @@ class CreateChatModel(BaseModel):
 
 # Currently, chat calls generates, so the params share the same one.
 CreateChatCompletionTorch = CreateCompletionTorch
-CreateChatCompletionLlamaCpp: BaseModel = CreateCompletionLlamaCpp
 
 
 from ._compat import CreateChatCompletionOpenAI
@@ -469,7 +399,6 @@ from ._compat import CreateChatCompletionOpenAI
 class CreateChatCompletion(  # type: ignore
     CreateChatModel,
     CreateChatCompletionTorch,
-    CreateChatCompletionLlamaCpp,
     CreateChatCompletionOpenAI,
 ):
     pass

xinference/web/ui/build/asset-manifest.json

@@ -1,14 +1,14 @@
 {
   "files": {
     "main.css": "./static/css/main.337afe76.css",
-    "main.js": "./static/js/main.91e77b5c.js",
+    "main.js": "./static/js/main.ae579a97.js",
     "static/media/icon.webp": "./static/media/icon.4603d52c63041e5dfbfd.webp",
     "index.html": "./index.html",
     "main.337afe76.css.map": "./static/css/main.337afe76.css.map",
-    "main.91e77b5c.js.map": "./static/js/main.91e77b5c.js.map"
+    "main.ae579a97.js.map": "./static/js/main.ae579a97.js.map"
   },
   "entrypoints": [
     "static/css/main.337afe76.css",
-    "static/js/main.91e77b5c.js"
+    "static/js/main.ae579a97.js"
   ]
 }

xinference/web/ui/build/index.html

@@ -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.91e77b5c.js"></script><link href="./static/css/main.337afe76.css" rel="stylesheet"></head><body><noscript>You need to enable JavaScript to run this app.</noscript><div id="root"></div></body></html>
+<!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.ae579a97.js"></script><link href="./static/css/main.337afe76.css" rel="stylesheet"></head><body><noscript>You need to enable JavaScript to run this app.</noscript><div id="root"></div></body></html>