xinference 0.14.2__py3-none-any.whl → 0.14.4__py3-none-any.whl

xinference/model/video/model_spec.json

@@ -6,6 +6,29 @@
     "model_revision": "4bbfb1de622b80bc1b77b6e9aced75f816be0e38",
     "model_ability": [
       "text2video"
-    ]
+    ],
+    "default_model_config": {
+      "scheduler": "CogVideoXDDIMScheduler",
+      "torch_dtype": "float16"
+    },
+    "default_generate_config": {
+      "guidance_scale": 6
+    }
+  },
+  {
+    "model_name": "CogVideoX-5b",
+    "model_family": "CogVideoX",
+    "model_id": "THUDM/CogVideoX-5b",
+    "model_revision": "8d6ea3f817438460b25595a120f109b88d5fdfad",
+    "model_ability": [
+      "text2video"
+    ],
+    "default_model_config": {
+      "scheduler": "CogVideoXDPMScheduler",
+      "torch_dtype": "bfloat16"
+    },
+    "default_generate_config": {
+      "guidance_scale": 7
+    }
   }
 ]

xinference/model/video/model_spec_modelscope.json

@@ -7,6 +7,30 @@
     "model_revision": "master",
     "model_ability": [
       "text2video"
-    ]
+    ],
+    "default_model_config": {
+      "scheduler": "CogVideoXDDIMScheduler",
+      "torch_dtype": "float16"
+    },
+    "default_generate_config": {
+      "guidance_scale": 6
+    }
+  },
+  {
+    "model_name": "CogVideoX-5b",
+    "model_family": "CogVideoX",
+    "model_hub": "modelscope",
+    "model_id": "ZhipuAI/CogVideoX-5b",
+    "model_revision": "master",
+    "model_ability": [
+      "text2video"
+    ],
+    "default_model_config": {
+      "scheduler": "CogVideoXDPMScheduler",
+      "torch_dtype": "bfloat16"
+    },
+    "default_generate_config": {
+      "guidance_scale": 7
+    }
   }
 ]

xinference/thirdparty/fish_speech/fish_speech/callbacks/__init__.py

@@ -0,0 +1,3 @@
+from .grad_norm import GradNormMonitor
+
+__all__ = ["GradNormMonitor"]

xinference/thirdparty/fish_speech/fish_speech/callbacks/grad_norm.py

@@ -0,0 +1,113 @@
+from typing import Optional, Union
+
+import lightning.pytorch as pl
+import torch
+from lightning import LightningModule, Trainer
+from lightning.pytorch.callbacks import Callback
+from torch import Tensor, nn
+from torch.utils._foreach_utils import (
+    _group_tensors_by_device_and_dtype,
+    _has_foreach_support,
+)
+
+
+@torch.no_grad()
+def grad_norm(
+    parameters: Union[Tensor, list[Tensor]],
+    norm_type: float = 2.0,
+) -> float:
+    """
+    Returns the norm of the gradients of the given parameters.
+
+    Args:
+        parameters (Iterable[Tensor] or Tensor): an iterable of Tensors or a
+            single Tensor that will have gradients normalized
+        norm_type (float): type of the used p-norm.
+
+    Returns:
+        Total norm of the parameter gradients (viewed as a single vector).
+    """  # noqa: E501
+
+    if isinstance(parameters, Tensor):
+        parameters = [parameters]
+
+    grads = [p.grad for p in parameters if p.grad is not None]
+    if len(grads) == 0:
+        return None
+
+    first_device = grads[0].device
+    grouped_grads: dict[
+        tuple[torch.device, torch.dtype], list[list[Tensor]]
+    ] = _group_tensors_by_device_and_dtype(
+        [[g.detach() for g in grads]]
+    )  # type: ignore[assignment]
+
+    norms = []
+    for (device, _), ([grads], _) in grouped_grads.items():
+        if _has_foreach_support(grads, device=device):
+            norms.extend(torch._foreach_norm(grads, norm_type))
+        else:
+            norms.extend([torch.norm(g, norm_type) for g in grads])
+
+    return torch.norm(torch.stack([norm.to(first_device) for norm in norms]), norm_type)
+
+
+class GradNormMonitor(Callback):
+    """
+    Callback that computes the gradient norm of the model parameters.
+    """
+
+    def __init__(
+        self,
+        norm_type: float = 2.0,
+        logging_interval: str = "step",
+        sub_module: Optional[Union[str, list[str]]] = None,
+    ) -> None:
+        """
+        Args:
+            norm_type (float): type of the used p-norm.
+            logging_interval (str): "step" or "epoch".
+        """
+        super().__init__()
+
+        self.norm_type = norm_type
+        self.logging_interval = logging_interval
+        self.sub_module = sub_module
+
+    def on_after_backward(self, trainer: Trainer, model: LightningModule) -> None:
+        """
+        Computes the gradient norm of the model parameters and logs it to the logger.
+
+        Args:
+            trainer (Trainer): The trainer object
+            model (LightningModule): The current lightningModule
+        """
+
+        lightning_model = model
+
+        if self.sub_module is None:
+            return self.log_sub_module_grad_norm(lightning_model, model, "")
+
+        sub_modules = self.sub_module
+        if isinstance(sub_modules, str):
+            sub_modules = [sub_modules]
+
+        for sub_module in sub_modules:
+            self.log_sub_module_grad_norm(
+                lightning_model, getattr(model, sub_module), f"/{sub_module}"
+            )
+
+    def log_sub_module_grad_norm(
+        self, lightning_model: LightningModule, model: nn.Module, path: str
+    ) -> None:
+        grad_norm_val = grad_norm(model.parameters(), self.norm_type)
+        if grad_norm_val is None:
+            return
+
+        on_step = self.logging_interval == "step"
+        lightning_model.log(
+            f"train{path}/grad_norm",
+            grad_norm_val,
+            on_step=on_step,
+            on_epoch=not on_step,
+        )

xinference/thirdparty/fish_speech/fish_speech/conversation.py

@@ -0,0 +1,2 @@
+SEMANTIC_TOKEN = "<|semantic|>"
+CODEBOOK_PAD_TOKEN_ID = 0

xinference/thirdparty/fish_speech/fish_speech/datasets/concat_repeat.py

@@ -0,0 +1,53 @@
+import bisect
+import random
+from typing import Iterable
+
+from torch.utils.data import Dataset, IterableDataset
+
+
+class ConcatRepeatDataset(Dataset):
+    datasets: list[Dataset]
+    cumulative_sizes: list[int]
+    repeats: list[int]
+
+    @staticmethod
+    def cumsum(sequence, repeats):
+        r, s = [], 0
+        for dataset, repeat in zip(sequence, repeats):
+            l = len(dataset) * repeat
+            r.append(l + s)
+            s += l
+        return r
+
+    def __init__(self, datasets: Iterable[Dataset], repeats: list[int]):
+        super().__init__()
+
+        self.datasets = list(datasets)
+        self.repeats = repeats
+
+        assert len(self.datasets) > 0, "datasets should not be an empty iterable"
+        assert len(self.datasets) == len(
+            repeats
+        ), "datasets and repeats should have the same length"
+
+        for d in self.datasets:
+            assert not isinstance(
+                d, IterableDataset
+            ), "ConcatRepeatDataset does not support IterableDataset"
+
+        self.cumulative_sizes = self.cumsum(self.datasets, self.repeats)
+
+    def __len__(self):
+        return self.cumulative_sizes[-1]
+
+    def __getitem__(self, idx):
+        dataset_idx = bisect.bisect_right(self.cumulative_sizes, idx)
+
+        if dataset_idx == 0:
+            sample_idx = idx
+        else:
+            sample_idx = idx - self.cumulative_sizes[dataset_idx - 1]
+
+        dataset = self.datasets[dataset_idx]
+
+        return dataset[sample_idx % len(dataset)]

xinference/thirdparty/fish_speech/fish_speech/datasets/protos/text_data_pb2.py

@@ -0,0 +1,33 @@
+# -*- coding: utf-8 -*-
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+# source: text-data.proto
+# Protobuf Python Version: 4.25.1
+"""Generated protocol buffer code."""
+from google.protobuf import descriptor as _descriptor
+from google.protobuf import descriptor_pool as _descriptor_pool
+from google.protobuf import symbol_database as _symbol_database
+from google.protobuf.internal import builder as _builder
+
+# @@protoc_insertion_point(imports)
+
+_sym_db = _symbol_database.Default()
+
+
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(
+    b'\n\x0ftext-data.proto\x12\ttext_data"\x1b\n\tSemantics\x12\x0e\n\x06values\x18\x01 \x03(\r"B\n\x08Sentence\x12\r\n\x05texts\x18\x01 \x03(\t\x12\'\n\tsemantics\x18\x03 \x03(\x0b\x32\x14.text_data.Semantics"P\n\x08TextData\x12\x0e\n\x06source\x18\x01 \x01(\t\x12\x0c\n\x04name\x18\x02 \x01(\t\x12&\n\tsentences\x18\x04 \x03(\x0b\x32\x13.text_data.Sentence"Q\n\x0bSampledData\x12\x0e\n\x06source\x18\x01 \x01(\t\x12\x0c\n\x04name\x18\x02 \x01(\t\x12$\n\x07samples\x18\x03 \x03(\x0b\x32\x13.text_data.Sentenceb\x06proto3'
+)
+
+_globals = globals()
+_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
+_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, "text_data_pb2", _globals)
+if _descriptor._USE_C_DESCRIPTORS == False:
+    DESCRIPTOR._options = None
+    _globals["_SEMANTICS"]._serialized_start = 30
+    _globals["_SEMANTICS"]._serialized_end = 57
+    _globals["_SENTENCE"]._serialized_start = 59
+    _globals["_SENTENCE"]._serialized_end = 125
+    _globals["_TEXTDATA"]._serialized_start = 127
+    _globals["_TEXTDATA"]._serialized_end = 207
+    _globals["_SAMPLEDDATA"]._serialized_start = 209
+    _globals["_SAMPLEDDATA"]._serialized_end = 290
+# @@protoc_insertion_point(module_scope)

xinference/thirdparty/fish_speech/fish_speech/datasets/protos/text_data_stream.py

@@ -0,0 +1,36 @@
+import struct
+
+from .text_data_pb2 import TextData
+
+
+def read_pb_stream(f):
+    while True:
+        buf = f.read(4)
+        if len(buf) == 0:
+            break
+        size = struct.unpack("I", buf)[0]
+        buf = f.read(size)
+        text_data = TextData()
+        text_data.ParseFromString(buf)
+        yield text_data
+
+
+def write_pb_stream(f, text_data):
+    buf = text_data.SerializeToString()
+    f.write(struct.pack("I", len(buf)))
+    f.write(buf)
+
+
+def pack_pb_stream(text_data):
+    buf = text_data.SerializeToString()
+    return struct.pack("I", len(buf)) + buf
+
+
+def split_pb_stream(f):
+    while True:
+        head = f.read(4)
+        if len(head) == 0:
+            break
+        size = struct.unpack("I", head)[0]
+        buf = f.read(size)
+        yield head + buf