搜索

按 Enter 键快速全文搜索，也可直接发起 AI 搜索
 首页 文库资料 文章资讯  上传文档  发布文章  登录账户

分类

全部综合其他(11)人工智能(11)

语言

全部英语(11)

格式

全部PDF文档 PDF(11)
 
本次搜索耗时 0.097 秒，为您找到相关结果约 11 个.

  • pdf文档 vLLM v0.5.1 Documentation

    multi_modal_data: This is a dictionary that follows the schema defined in vllm.multimodal. MultiModalDataDict. # Refer to the HuggingFace repo for the correct format to use prompt = "USER: ![]()\nWhat be tokenized before passing to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ```python class A list of token IDs to pass to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ## 1.37 vLLM Engine
    0 码力 | 162 页 | 1.14 MB | 3 月前
    3

  • pdf文档 vLLM v0.5.4 Documentation

    multi_modal_data: This is a dictionary that follows the schema defined in vllm.multimodal. MultiModalDataDict. ```python # Refer to the HuggingFace repo for the correct format to use prompt = "USER: be tokenized before passing to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ```python class A list of token IDs to pass to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ## 1.41 vLLM Engine
    0 码力 | 152 页 | 1.10 MB | 3 月前
    3

  • pdf文档 vLLM v0.5.2 Documentation

    multi_modal_data: This is a dictionary that follows the schema defined in vllm.multimodal. MultiModalDataDict. ```python # Refer to the HuggingFace repo for the correct format to use prompt = "USER: be tokenized before passing to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ```python class A list of token IDs to pass to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ## 1.40 vLLM Engine
    0 码力 | 166 页 | 1.15 MB | 3 月前
    3

  • pdf文档 vLLM v0.5.3.post1 Documentation

    multi_modal_data: This is a dictionary that follows the schema defined in vllm.multimodal. MultiModalDataDict. ```python # Refer to the HuggingFace repo for the correct format to use prompt = "USER: be tokenized before passing to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ```python class A list of token IDs to pass to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ## 1.39 vLLM Engine
    0 码力 | 143 页 | 1.07 MB | 3 月前
    3

  • pdf文档 vLLM v0.5.3 Documentation

    multi_modal_data: This is a dictionary that follows the schema defined in vllm.multimodal. MultiModalDataDict. ```python # Refer to the HuggingFace repo for the correct format to use prompt = "USER: be tokenized before passing to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ```python class A list of token IDs to pass to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ## 1.39 vLLM Engine
    0 码力 | 143 页 | 1.07 MB | 3 月前
    3

  • pdf文档 vLLM v0.5.5 Documentation

    multi_modal_data: This is a dictionary that follows the schema defined in vllm.multimodal. MultiModalDataDict. # Refer to the HuggingFace repo for the correct format to use prompt = "USER: ![]()\nWhat be tokenized before passing to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ass vllm.inputs A list of token IDs to pass to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ## 1.42 vLLM Engine
    0 码力 | 193 页 | 1.22 MB | 3 月前
    5

  • pdf文档 vLLM v0.6.0 Documentation

    multi_modal_data: This is a dictionary that follows the schema defined in vllm.multimodal. MultiModalDataDict. # Refer to the HuggingFace repo for the correct format to use prompt = "USER: ![]()\nWhat be tokenized before passing to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. class vllm.inputs A list of token IDs to pass to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ## 1.42 vLLM Engine
    0 码力 | 201 页 | 1.26 MB | 3 月前
    3

  • pdf文档 vLLM v0.6.1.post2 Documentation

    multi_modal_data: This is a dictionary that follows the schema defined in vllm.multimodal. MultiModalDataDict. ```python # Refer to the HuggingFace repo for the correct format to use prompt = "USER: be tokenized before passing to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. class vllm.inputs A list of token IDs to pass to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ## 1.42 vLLM Engine
    0 码力 | 215 页 | 1.29 MB | 3 月前
    3

  • pdf文档 vLLM v0.6.1 Documentation

    multi_modal_data: This is a dictionary that follows the schema defined in vllm.multimodal. MultiModalDataDict. # Refer to the HuggingFace repo for the correct format to use prompt = "USER: ![]()\nWhat be tokenized before passing to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. class vllm.inputs A list of token IDs to pass to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ## 1.42 vLLM Engine
    0 码力 | 215 页 | 1.29 MB | 3 月前
    3

  • pdf文档 vLLM v0.6.1.post1 Documentation

    multi_modal_data: This is a dictionary that follows the schema defined in vllm.multimodal. MultiModalDataDict. ```python # Refer to the HuggingFace repo for the correct format to use prompt = "USER: be tokenized before passing to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. class vllm.inputs A list of token IDs to pass to the model. multi_modal_data: typing_extensions.NotRequired[MultiModalDataDict] Optional multi-modal data to pass to the model, if the model supports it. ## 1.42 vLLM Engine
    0 码力 | 215 页 | 1.28 MB | 3 月前
    3
共 11 条
  • 1
  • 2
前往
页
相关搜索词
Vision Language ModelsOffline Batched InferencePreemptionChunked PrefillMultiModalDataDictvLLMpaged attention多模态数据连续批量处理预emptionLLM inferenceproduction metricsusage statisticsmulti-modal modelsmulti_modal_datapreemptionchunked prefillLLMperformance tuning性能基准测试KV缓存管理模型集成参数配置PagedAttention量化分批处理LoRA AdapterPerformance TuningSampling ParametersKV cacheLoRA多模态模型LoRA adapterVision Language Models (VLMs)