Upload inference code

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 language_model_w8a8.rkllm filter=lfs diff=lfs merge=lfs -text
 vision_encoder.rknn filter=lfs diff=lfs merge=lfs -text
+librkllmrt.so filter=lfs diff=lfs merge=lfs -text

export_vision_onnx.py

@@ -0,0 +1,89 @@
+import numpy as np
+import os
+import torch
+from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer
+import torch.nn.functional as F
+import argparse
+
+argparse = argparse.ArgumentParser()
+argparse.add_argument('--step', type=int, help='export step', required=True)
+argparse.add_argument('--path', type=str, default='.', help='model path', required=False)
+argparse.add_argument('--batch', type=int, default=1, help='batch size', required=False)
+argparse.add_argument('--height', type=int, default=448, help='image height', required=False)
+argparse.add_argument('--width', type=int, default=448, help='image width', required=False)
+argparse.add_argument('--savepath', type=str, default='vision_encoder.onnx', help='save path', required=False)
+args = argparse.parse_args()
+
+step = args.step
+# 加载本地模型
+path = args.path
+model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+    path,
+    torch_dtype=torch.float32, # 注意此处的数据类型，由于 rknn 目前仅支持 float32 ，因此需要指定；若是在加载权重时限制了数据类型，需要自行修改config.json中的 "use_flash_attn" 参数为 false
+    low_cpu_mem_usage=True,
+    trust_remote_code=True).eval()
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
+
+N = args.batch                           # batch size
+channel = 3                                 # 3 for RGB
+H = args.height                         # image height, must be divisible by (merge_size * patch_size)
+W = args.width                          # image width, must be divisible by (merge_size * patch_size)
+merge_size = 2
+temporal_patch_size = 2
+patch_size = 14
+grid_t = N // temporal_patch_size if N%temporal_patch_size == 0 else N // temporal_patch_size + 1
+grid_h = H // patch_size
+grid_w = W // patch_size
+
+def export_onnx(image):
+    if N == 1:
+        images = image.repeat(temporal_patch_size, 1, 1, 1)
+    elif N % temporal_patch_size != 0:
+        repeat_time = temporal_patch_size - N % temporal_patch_size
+        repeat_image = image[-1:, ...].repeat(repeat_time, 1, 1, 1)
+        images = torch.cat((image, repeat_image), dim=0)
+    patches = images.reshape(grid_t, temporal_patch_size, channel, grid_h//merge_size, merge_size, patch_size, grid_w//merge_size, merge_size, patch_size)
+    patches = patches.permute(0, 3, 6, 4, 7, 2, 1, 5, 8)
+    flatten_patches = patches.reshape(grid_t * grid_h * grid_w, channel * temporal_patch_size * patch_size * patch_size)
+    model.visual.forward = forward_new(model.visual)
+    if step == 1:
+        feature = model.visual(flatten_patches, torch.tensor([grid_t, grid_h, grid_w]).unsqueeze(0))
+    else:
+        feature = model.visual(flatten_patches)
+    return feature
+
+def forward_new(self):
+    def tmp (hidden_states, grid_thw=None):
+        hidden_states = self.patch_embed(hidden_states)
+        if grid_thw is not None:
+            rotary_pos_emb = self.rot_pos_emb(grid_thw)
+            cu_seqlens = torch.repeat_interleave(grid_thw[:, 1] * grid_thw[:, 2], grid_thw[:, 0]).cumsum(
+                dim=0, dtype=torch.int32
+            )
+            cu_seqlens = F.pad(cu_seqlens, (1, 0), value=0)
+            np.save("./rotary_pos_emb.npy", rotary_pos_emb.cpu().detach().numpy())
+            np.save("./cu_seqlens.npy", cu_seqlens.cpu().detach().numpy())
+        else:
+            rotary_pos_emb = torch.from_numpy(np.load("./rotary_pos_emb.npy")).to(dtype=hidden_states.dtype, device=hidden_states.device)
+            cu_seqlens = torch.from_numpy(np.load("./cu_seqlens.npy")).to(dtype=torch.int32, device=hidden_states.device)
+        
+        for blk in self.blocks:
+            hidden_states = blk(hidden_states, cu_seqlens=cu_seqlens, rotary_pos_emb=rotary_pos_emb)
+
+        return self.merger(hidden_states)
+    return tmp
+
+# 导出 Vison 部分所对应的 onnx 模型，假设输入是2x3x392x392->(28x28)x(3x2x14x14)
+# pixel_values = torch.randn(784, 1176, device="cuda", dtype=torch.float32)
+pixel_values = torch.randn(N, channel, H, W, device="cpu", dtype=torch.float32)
+model.forward = export_onnx
+model = model.to(torch.float32).eval()
+if step == 1:
+    print("==========================================================")
+    print("Generating the rotary_pos_emb and cu_seqlens done.")
+    feature = model(pixel_values)
+else:
+    print("==========================================================")
+    print(f"Exporting the vision part of {path} to onnx format.")
+    # os.makedirs(os.path.dirname(args.savepath), exist_ok=True)
+    torch.onnx.export(model, pixel_values, args.savepath, opset_version=17)

librkllmrt.so

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e6f87f07bbb08058cad4871cc74e8069a054fe4f6259b43c29a4738b0affdd
+size 7461896

rkllm-convert.py

@@ -0,0 +1,23 @@
+from rkllm.api import RKLLM
+
+modelpath = '.'
+llm = RKLLM()
+
+ret = llm.load_huggingface(model=modelpath, model_lora=None, device='cpu')
+if ret != 0:
+    print('Load model failed!')
+    exit(ret)
+
+qparams = None
+ret = llm.build(do_quantization=True, optimization_level=1, quantized_dtype='w8a8',
+                quantized_algorithm='normal', target_platform='rk3588', num_npu_core=3, extra_qparams=qparams)
+
+if ret != 0:
+    print('Build model failed!')
+    exit(ret)
+
+# Export rkllm model
+ret = llm.export_rkllm("./language_model.rkllm")
+if ret != 0:
+    print('Export model failed!')
+    exit(ret)

rkllm_binding.py

@@ -0,0 +1,873 @@
+import ctypes
+import enum
+import os
+
+# Define constants from the header
+CPU0 = (1 << 0)  # 0x01
+CPU1 = (1 << 1)  # 0x02
+CPU2 = (1 << 2)  # 0x04
+CPU3 = (1 << 3)  # 0x08
+CPU4 = (1 << 4)  # 0x10
+CPU5 = (1 << 5)  # 0x20
+CPU6 = (1 << 6)  # 0x40
+CPU7 = (1 << 7)  # 0x80
+
+# --- Enums ---
+class LLMCallState(enum.IntEnum):
+    RKLLM_RUN_NORMAL = 0
+    RKLLM_RUN_WAITING = 1
+    RKLLM_RUN_FINISH = 2
+    RKLLM_RUN_ERROR = 3
+
+class RKLLMInputType(enum.IntEnum):
+    RKLLM_INPUT_PROMPT = 0
+    RKLLM_INPUT_TOKEN = 1
+    RKLLM_INPUT_EMBED = 2
+    RKLLM_INPUT_MULTIMODAL = 3
+
+class RKLLMInferMode(enum.IntEnum):
+    RKLLM_INFER_GENERATE = 0
+    RKLLM_INFER_GET_LAST_HIDDEN_LAYER = 1
+    RKLLM_INFER_GET_LOGITS = 2
+
+# --- Structures ---
+class RKLLMExtendParam(ctypes.Structure):
+    base_domain_id: ctypes.c_int32
+    embed_flash: ctypes.c_int8
+    enabled_cpus_num: ctypes.c_int8
+    enabled_cpus_mask: ctypes.c_uint32
+    n_batch: ctypes.c_uint8
+    use_cross_attn: ctypes.c_int8
+    reserved: ctypes.c_uint8 * 104
+
+    _fields_ = [
+        ("base_domain_id", ctypes.c_int32),     # 基础域ID
+        ("embed_flash", ctypes.c_int8),         # 是否从闪存查询词嵌入向量（1启用，0禁用）
+        ("enabled_cpus_num", ctypes.c_int8),    # 推理启用的CPU数量
+        ("enabled_cpus_mask", ctypes.c_uint32), # 指示启用哪些CPU的位掩码
+        ("n_batch", ctypes.c_uint8),            # 一次前向传播中并发处理的输入样本数，设置>1启用批量推理，默认为1
+        ("use_cross_attn", ctypes.c_int8),      # 是否启用交叉注意力（非零启用，0禁用）
+        ("reserved", ctypes.c_uint8 * 104)     # 保留字段
+    ]
+
+class RKLLMParam(ctypes.Structure):
+    model_path: ctypes.c_char_p
+    max_context_len: ctypes.c_int32
+    max_new_tokens: ctypes.c_int32
+    top_k: ctypes.c_int32
+    n_keep: ctypes.c_int32
+    top_p: ctypes.c_float
+    temperature: ctypes.c_float
+    repeat_penalty: ctypes.c_float
+    frequency_penalty: ctypes.c_float
+    presence_penalty: ctypes.c_float
+    mirostat: ctypes.c_int32
+    mirostat_tau: ctypes.c_float
+    mirostat_eta: ctypes.c_float
+    skip_special_token: ctypes.c_bool
+    is_async: ctypes.c_bool
+    img_start: ctypes.c_char_p
+    img_end: ctypes.c_char_p
+    img_content: ctypes.c_char_p
+    extend_param: RKLLMExtendParam
+
+    _fields_ = [
+        ("model_path", ctypes.c_char_p),         # 模型文件路径
+        ("max_context_len", ctypes.c_int32),     # 上下文窗口最大token数
+        ("max_new_tokens", ctypes.c_int32),      # 最大生成新token数
+        ("top_k", ctypes.c_int32),               # Top-K采样参数
+        ("n_keep", ctypes.c_int32),              # 上下文窗口移动时保留的kv缓存数量
+        ("top_p", ctypes.c_float),               # Top-P（nucleus）采样参数
+        ("temperature", ctypes.c_float),         # 采样温度，影响token选择的随机性
+        ("repeat_penalty", ctypes.c_float),      # 重复token惩罚
+        ("frequency_penalty", ctypes.c_float),   # 频繁token惩罚
+        ("presence_penalty", ctypes.c_float),    # 输入中已存在token的惩罚
+        ("mirostat", ctypes.c_int32),            # Mirostat采样策略标志（0表示禁用）
+        ("mirostat_tau", ctypes.c_float),        # Mirostat采样Tau参数
+        ("mirostat_eta", ctypes.c_float),        # Mirostat采样Eta参数
+        ("skip_special_token", ctypes.c_bool),   # 是否跳过特殊token
+        ("is_async", ctypes.c_bool),             # 是否异步推理
+        ("img_start", ctypes.c_char_p),          # 多模态输入中图像的起始位置
+        ("img_end", ctypes.c_char_p),            # 多模态输入中图像的结束位置
+        ("img_content", ctypes.c_char_p),        # 图像内容指针
+        ("extend_param", RKLLMExtendParam)       # 扩展参数
+    ]
+
+class RKLLMLoraAdapter(ctypes.Structure):
+    lora_adapter_path: ctypes.c_char_p
+    lora_adapter_name: ctypes.c_char_p
+    scale: ctypes.c_float
+
+    _fields_ = [
+        ("lora_adapter_path", ctypes.c_char_p),
+        ("lora_adapter_name", ctypes.c_char_p),
+        ("scale", ctypes.c_float)
+    ]
+
+class RKLLMEmbedInput(ctypes.Structure):
+    embed: ctypes.POINTER(ctypes.c_float)
+    n_tokens: ctypes.c_size_t
+
+    _fields_ = [
+        ("embed", ctypes.POINTER(ctypes.c_float)),
+        ("n_tokens", ctypes.c_size_t)
+    ]
+
+class RKLLMTokenInput(ctypes.Structure):
+    input_ids: ctypes.POINTER(ctypes.c_int32)
+    n_tokens: ctypes.c_size_t
+
+    _fields_ = [
+        ("input_ids", ctypes.POINTER(ctypes.c_int32)),
+        ("n_tokens", ctypes.c_size_t)
+    ]
+
+class RKLLMMultiModelInput(ctypes.Structure):
+    prompt: ctypes.c_char_p
+    image_embed: ctypes.POINTER(ctypes.c_float)
+    n_image_tokens: ctypes.c_size_t
+    n_image: ctypes.c_size_t
+    image_width: ctypes.c_size_t
+    image_height: ctypes.c_size_t
+
+    _fields_ = [
+        ("prompt", ctypes.c_char_p),
+        ("image_embed", ctypes.POINTER(ctypes.c_float)),
+        ("n_image_tokens", ctypes.c_size_t),
+        ("n_image", ctypes.c_size_t),
+        ("image_width", ctypes.c_size_t),
+        ("image_height", ctypes.c_size_t)
+    ]
+
+class RKLLMCrossAttnParam(ctypes.Structure):
+    """
+    交叉注意力参数结构体
+    
+    该结构体用于在解码器中执行交叉注意力时使用。
+    它提供编码器输出（键/值缓存）、位置索引和注意力掩码。
+    
+    - encoder_k_cache必须存储在连续内存中，布局为：
+      [num_layers][num_tokens][num_kv_heads][head_dim]
+    - encoder_v_cache必须存储在连续内存中，布局为：
+      [num_layers][num_kv_heads][head_dim][num_tokens]
+    """
+    encoder_k_cache: ctypes.POINTER(ctypes.c_float)
+    encoder_v_cache: ctypes.POINTER(ctypes.c_float)
+    encoder_mask: ctypes.POINTER(ctypes.c_float)
+    encoder_pos: ctypes.POINTER(ctypes.c_int32)
+    num_tokens: ctypes.c_int
+
+    _fields_ = [
+        ("encoder_k_cache", ctypes.POINTER(ctypes.c_float)),  # 编码器键缓存指针（大小：num_layers * num_tokens * num_kv_heads * head_dim）
+        ("encoder_v_cache", ctypes.POINTER(ctypes.c_float)),  # 编码器值缓存指针（大小：num_layers * num_kv_heads * head_dim * num_tokens）
+        ("encoder_mask", ctypes.POINTER(ctypes.c_float)),     # 编码器注意力掩码指针（大小：num_tokens的数组）
+        ("encoder_pos", ctypes.POINTER(ctypes.c_int32)),      # 编码器token位置指针（大小：num_tokens的数组）
+        ("num_tokens", ctypes.c_int)                          # 编码器序列中的token数量
+    ]
+
+class RKLLMPerfStat(ctypes.Structure):
+    """
+    性能统计结构体
+    
+    用于保存预填充和生成阶段的性能统计信息。
+    """
+    prefill_time_ms: ctypes.c_float
+    prefill_tokens: ctypes.c_int
+    generate_time_ms: ctypes.c_float
+    generate_tokens: ctypes.c_int
+    memory_usage_mb: ctypes.c_float
+
+    _fields_ = [
+        ("prefill_time_ms", ctypes.c_float),   # 预填充阶段总耗时（毫秒）
+        ("prefill_tokens", ctypes.c_int),      # 预填充阶段处理的token数量
+        ("generate_time_ms", ctypes.c_float),  # 生成阶段总耗时（毫秒）
+        ("generate_tokens", ctypes.c_int),     # 生成阶段处理的token数量
+        ("memory_usage_mb", ctypes.c_float)    # 推理期间VmHWM常驻内存使用量（MB）
+    ]
+
+class _RKLLMInputUnion(ctypes.Union):
+    prompt_input: ctypes.c_char_p
+    embed_input: RKLLMEmbedInput
+    token_input: RKLLMTokenInput
+    multimodal_input: RKLLMMultiModelInput
+
+    _fields_ = [
+        ("prompt_input", ctypes.c_char_p),
+        ("embed_input", RKLLMEmbedInput),
+        ("token_input", RKLLMTokenInput),
+        ("multimodal_input", RKLLMMultiModelInput)
+    ]
+
+class RKLLMInput(ctypes.Structure):
+    """
+    LLM输入结构体
+    
+    通过联合体表示不同类型的LLM输入。
+    """
+    role: ctypes.c_char_p
+    enable_thinking: ctypes.c_bool
+    input_type: ctypes.c_int
+    _union_data: _RKLLMInputUnion
+
+    _fields_ = [
+        ("role", ctypes.c_char_p),              # 消息角色："user"（用户输入）、"tool"（函数结果）
+        ("enable_thinking", ctypes.c_bool),     # 控制Qwen3模型是否启用"思考模式"
+        ("input_type", ctypes.c_int),           # 枚举类型，指定输入类型（如prompt、token、embed、multimodal）
+        ("_union_data", _RKLLMInputUnion)       # 联合体数据
+    ]
+    # Properties to make accessing union members easier
+    @property
+    def prompt_input(self) -> bytes: # Assuming c_char_p maps to bytes
+        if self.input_type == RKLLMInputType.RKLLM_INPUT_PROMPT:
+            return self._union_data.prompt_input
+        raise AttributeError("Not a prompt input")
+    @prompt_input.setter
+    def prompt_input(self, value: bytes): # Assuming c_char_p maps to bytes
+        if self.input_type == RKLLMInputType.RKLLM_INPUT_PROMPT:
+            self._union_data.prompt_input = value
+        else:
+            raise AttributeError("Not a prompt input")
+    @property
+    def embed_input(self) -> RKLLMEmbedInput:
+        if self.input_type == RKLLMInputType.RKLLM_INPUT_EMBED:
+            return self._union_data.embed_input
+        raise AttributeError("Not an embed input")
+    @embed_input.setter
+    def embed_input(self, value: RKLLMEmbedInput):
+        if self.input_type == RKLLMInputType.RKLLM_INPUT_EMBED:
+            self._union_data.embed_input = value
+        else:
+            raise AttributeError("Not an embed input")
+
+    @property
+    def token_input(self) -> RKLLMTokenInput:
+        if self.input_type == RKLLMInputType.RKLLM_INPUT_TOKEN:
+            return self._union_data.token_input
+        raise AttributeError("Not a token input")
+    @token_input.setter
+    def token_input(self, value: RKLLMTokenInput):
+        if self.input_type == RKLLMInputType.RKLLM_INPUT_TOKEN:
+            self._union_data.token_input = value
+        else:
+            raise AttributeError("Not a token input")
+
+    @property
+    def multimodal_input(self) -> RKLLMMultiModelInput:
+        if self.input_type == RKLLMInputType.RKLLM_INPUT_MULTIMODAL:
+            return self._union_data.multimodal_input
+        raise AttributeError("Not a multimodal input")
+    @multimodal_input.setter
+    def multimodal_input(self, value: RKLLMMultiModelInput):
+        if self.input_type == RKLLMInputType.RKLLM_INPUT_MULTIMODAL:
+            self._union_data.multimodal_input = value
+        else:
+            raise AttributeError("Not a multimodal input")
+
+class RKLLMLoraParam(ctypes.Structure): # For inference
+    lora_adapter_name: ctypes.c_char_p
+
+    _fields_ = [
+        ("lora_adapter_name", ctypes.c_char_p)
+    ]
+
+class RKLLMPromptCacheParam(ctypes.Structure): # For inference
+    save_prompt_cache: ctypes.c_int # bool-like
+    prompt_cache_path: ctypes.c_char_p
+
+    _fields_ = [
+        ("save_prompt_cache", ctypes.c_int), # bool-like
+        ("prompt_cache_path", ctypes.c_char_p)
+    ]
+
+class RKLLMInferParam(ctypes.Structure):
+    mode: ctypes.c_int
+    lora_params: ctypes.POINTER(RKLLMLoraParam)
+    prompt_cache_params: ctypes.POINTER(RKLLMPromptCacheParam)
+    keep_history: ctypes.c_int # bool-like
+
+    _fields_ = [
+        ("mode", ctypes.c_int), # Enum will be passed as int, changed RKLLMInferMode to ctypes.c_int
+        ("lora_params", ctypes.POINTER(RKLLMLoraParam)),
+        ("prompt_cache_params", ctypes.POINTER(RKLLMPromptCacheParam)),
+        ("keep_history", ctypes.c_int) # bool-like
+    ]
+
+class RKLLMResultLastHiddenLayer(ctypes.Structure):
+    hidden_states: ctypes.POINTER(ctypes.c_float)
+    embd_size: ctypes.c_int
+    num_tokens: ctypes.c_int
+
+    _fields_ = [
+        ("hidden_states", ctypes.POINTER(ctypes.c_float)),
+        ("embd_size", ctypes.c_int),
+        ("num_tokens", ctypes.c_int)
+    ]
+
+class RKLLMResultLogits(ctypes.Structure):
+    logits: ctypes.POINTER(ctypes.c_float)
+    vocab_size: ctypes.c_int
+    num_tokens: ctypes.c_int
+
+    _fields_ = [
+        ("logits", ctypes.POINTER(ctypes.c_float)),
+        ("vocab_size", ctypes.c_int),
+        ("num_tokens", ctypes.c_int)
+    ]
+
+class RKLLMResult(ctypes.Structure):
+    """
+    LLM推理结果结构体
+    
+    表示LLM推理的结果，包含生成的文本、token ID、隐藏层状态、logits和性能统计。
+    """
+    text: ctypes.c_char_p
+    token_id: ctypes.c_int32
+    last_hidden_layer: RKLLMResultLastHiddenLayer
+    logits: RKLLMResultLogits
+    perf: RKLLMPerfStat
+
+    _fields_ = [
+        ("text", ctypes.c_char_p),                                  # 生成的文本结果
+        ("token_id", ctypes.c_int32),                              # 生成的token ID
+        ("last_hidden_layer", RKLLMResultLastHiddenLayer),         # 最后一层的隐藏状态（如果请求的话）
+        ("logits", RKLLMResultLogits),                             # 模型输出的logits
+        ("perf", RKLLMPerfStat)                                    # 性能统计（预填充和生成）
+    ]
+
+# --- Typedefs ---
+LLMHandle = ctypes.c_void_p
+
+# --- Callback Function Type ---
+LLMResultCallback = ctypes.CFUNCTYPE(
+    ctypes.c_int,  # 返回类型：int，表示处理状态
+    ctypes.POINTER(RKLLMResult),  # LLM结果指针
+    ctypes.c_void_p,              # 用户数据指针
+    ctypes.c_int                  # LLM调用状态（LLMCallState枚举值）
+)
+"""
+回调函数类型定义
+
+用于处理LLM结果的回调函数。
+
+参数：
+- result: 指向LLM结果的指针
+- userdata: 回调的用户数据指针  
+- state: LLM调用状态（例如：完成、错误）
+
+返回值：
+- 0: 正常继续推理
+- 1: 暂停推理。如果用户想要修改或干预结果（例如编辑输出、注入新提示），
+     返回1以暂停当前推理。稍后，使用更新的内容调用rkllm_run来恢复推理。
+"""
+
+class RKLLMRuntime:
+    def __init__(self, library_path="./librkllmrt.so"):
+        try:
+            self.lib = ctypes.CDLL(library_path)
+        except OSError as e:
+            raise OSError(f"Failed to load RKLLM library from {library_path}. "
+                          f"Ensure it's in your LD_LIBRARY_PATH or provide the full path. Error: {e}")
+        self._setup_functions()
+        self.llm_handle = LLMHandle()
+        self._c_callback = None # To keep the callback object alive
+
+    def _setup_functions(self):
+        # RKLLMParam rkllm_createDefaultParam();
+        self.lib.rkllm_createDefaultParam.restype = RKLLMParam
+        self.lib.rkllm_createDefaultParam.argtypes = []
+
+        # int rkllm_init(LLMHandle* handle, RKLLMParam* param, LLMResultCallback callback);
+        self.lib.rkllm_init.restype = ctypes.c_int
+        self.lib.rkllm_init.argtypes = [
+            ctypes.POINTER(LLMHandle),
+            ctypes.POINTER(RKLLMParam),
+            LLMResultCallback
+        ]
+
+        # int rkllm_load_lora(LLMHandle handle, RKLLMLoraAdapter* lora_adapter);
+        self.lib.rkllm_load_lora.restype = ctypes.c_int
+        self.lib.rkllm_load_lora.argtypes = [LLMHandle, ctypes.POINTER(RKLLMLoraAdapter)]
+
+        # int rkllm_load_prompt_cache(LLMHandle handle, const char* prompt_cache_path);
+        self.lib.rkllm_load_prompt_cache.restype = ctypes.c_int
+        self.lib.rkllm_load_prompt_cache.argtypes = [LLMHandle, ctypes.c_char_p]
+
+        # int rkllm_release_prompt_cache(LLMHandle handle);
+        self.lib.rkllm_release_prompt_cache.restype = ctypes.c_int
+        self.lib.rkllm_release_prompt_cache.argtypes = [LLMHandle]
+
+        # int rkllm_destroy(LLMHandle handle);
+        self.lib.rkllm_destroy.restype = ctypes.c_int
+        self.lib.rkllm_destroy.argtypes = [LLMHandle]
+
+        # int rkllm_run(LLMHandle handle, RKLLMInput* rkllm_input, RKLLMInferParam* rkllm_infer_params, void* userdata);
+        self.lib.rkllm_run.restype = ctypes.c_int
+        self.lib.rkllm_run.argtypes = [
+            LLMHandle,
+            ctypes.POINTER(RKLLMInput),
+            ctypes.POINTER(RKLLMInferParam),
+            ctypes.c_void_p # userdata
+        ]
+
+        # int rkllm_run_async(LLMHandle handle, RKLLMInput* rkllm_input, RKLLMInferParam* rkllm_infer_params, void* userdata);
+        # Assuming async also takes userdata for the callback context
+        self.lib.rkllm_run_async.restype = ctypes.c_int
+        self.lib.rkllm_run_async.argtypes = [
+            LLMHandle,
+            ctypes.POINTER(RKLLMInput),
+            ctypes.POINTER(RKLLMInferParam),
+            ctypes.c_void_p # userdata
+        ]
+
+        # int rkllm_abort(LLMHandle handle);
+        self.lib.rkllm_abort.restype = ctypes.c_int
+        self.lib.rkllm_abort.argtypes = [LLMHandle]
+
+        # int rkllm_is_running(LLMHandle handle);
+        self.lib.rkllm_is_running.restype = ctypes.c_int # 0 if running, non-zero otherwise
+        self.lib.rkllm_is_running.argtypes = [LLMHandle]
+
+        # int rkllm_clear_kv_cache(LLMHandle handle, int keep_system_prompt, int* start_pos, int* end_pos);
+        self.lib.rkllm_clear_kv_cache.restype = ctypes.c_int
+        self.lib.rkllm_clear_kv_cache.argtypes = [
+            LLMHandle, 
+            ctypes.c_int,
+            ctypes.POINTER(ctypes.c_int),  # start_pos
+            ctypes.POINTER(ctypes.c_int)   # end_pos
+        ]
+
+        # int rkllm_get_kv_cache_size(LLMHandle handle, int* cache_sizes);
+        self.lib.rkllm_get_kv_cache_size.restype = ctypes.c_int
+        self.lib.rkllm_get_kv_cache_size.argtypes = [LLMHandle, ctypes.POINTER(ctypes.c_int)]
+
+        # int rkllm_set_chat_template(LLMHandle handle, const char* system_prompt, const char* prompt_prefix, const char* prompt_postfix);
+        self.lib.rkllm_set_chat_template.restype = ctypes.c_int
+        self.lib.rkllm_set_chat_template.argtypes = [
+            LLMHandle,
+            ctypes.c_char_p,
+            ctypes.c_char_p,
+            ctypes.c_char_p
+        ]
+
+        # int rkllm_set_function_tools(LLMHandle handle, const char* system_prompt, const char* tools, const char* tool_response_str);
+        self.lib.rkllm_set_function_tools.restype = ctypes.c_int
+        self.lib.rkllm_set_function_tools.argtypes = [
+            LLMHandle,
+            ctypes.c_char_p,  # system_prompt
+            ctypes.c_char_p,  # tools
+            ctypes.c_char_p   # tool_response_str
+        ]
+
+        # int rkllm_set_cross_attn_params(LLMHandle handle, RKLLMCrossAttnParam* cross_attn_params);
+        self.lib.rkllm_set_cross_attn_params.restype = ctypes.c_int
+        self.lib.rkllm_set_cross_attn_params.argtypes = [LLMHandle, ctypes.POINTER(RKLLMCrossAttnParam)]
+
+    def create_default_param(self) -> RKLLMParam:
+        """Creates a default RKLLMParam structure."""
+        return self.lib.rkllm_createDefaultParam()
+
+    def init(self, param: RKLLMParam, callback_func) -> int:
+        """
+        Initializes the LLM.
+        :param param: RKLLMParam structure.
+        :param callback_func: A Python function that matches the signature:
+                              def my_callback(result_ptr, userdata_ptr, state_enum):
+                                  result = result_ptr.contents # RKLLMResult
+                                  # Process result
+                                  # userdata can be retrieved if passed during run, or ignored
+                                  # state = LLMCallState(state_enum)
+        :return: 0 for success, non-zero for failure.
+        """
+        if not callable(callback_func):
+            raise ValueError("callback_func must be a callable Python function.")
+
+        # Keep a reference to the ctypes callback object to prevent it from being garbage collected
+        self._c_callback = LLMResultCallback(callback_func)
+        
+        ret = self.lib.rkllm_init(ctypes.byref(self.llm_handle), ctypes.byref(param), self._c_callback)
+        if ret != 0:
+            raise RuntimeError(f"rkllm_init failed with error code {ret}")
+        return ret
+
+    def load_lora(self, lora_adapter: RKLLMLoraAdapter) -> int:
+        """Loads a Lora adapter."""
+        ret = self.lib.rkllm_load_lora(self.llm_handle, ctypes.byref(lora_adapter))
+        if ret != 0:
+            raise RuntimeError(f"rkllm_load_lora failed with error code {ret}")
+        return ret
+
+    def load_prompt_cache(self, prompt_cache_path: str) -> int:
+        """Loads a prompt cache from a file."""
+        c_path = prompt_cache_path.encode('utf-8')
+        ret = self.lib.rkllm_load_prompt_cache(self.llm_handle, c_path)
+        if ret != 0:
+            raise RuntimeError(f"rkllm_load_prompt_cache failed for {prompt_cache_path} with error code {ret}")
+        return ret
+
+    def release_prompt_cache(self) -> int:
+        """Releases the prompt cache from memory."""
+        ret = self.lib.rkllm_release_prompt_cache(self.llm_handle)
+        if ret != 0:
+            raise RuntimeError(f"rkllm_release_prompt_cache failed with error code {ret}")
+        return ret
+
+    def destroy(self) -> int:
+        """Destroys the LLM instance and releases resources."""
+        if self.llm_handle and self.llm_handle.value: # Check if handle is not NULL
+            ret = self.lib.rkllm_destroy(self.llm_handle)
+            self.llm_handle = LLMHandle() # Reset handle
+            if ret != 0:
+                # Don't raise here as it might be called in __del__
+                print(f"Warning: rkllm_destroy failed with error code {ret}") 
+            return ret
+        return 0 # Already destroyed or not initialized
+
+    def run(self, rkllm_input: RKLLMInput, rkllm_infer_params: RKLLMInferParam, userdata=None) -> int:
+        """Runs an LLM inference task synchronously."""
+        # userdata can be a ctypes.py_object if you want to pass Python objects,
+        # then cast to c_void_p. Or simply None.
+        if userdata is not None:
+            # Store the userdata object to keep it alive during the call
+            self._userdata_ref = userdata
+            c_userdata = ctypes.cast(ctypes.pointer(ctypes.py_object(userdata)), ctypes.c_void_p)
+        else:
+            c_userdata = None
+        ret = self.lib.rkllm_run(self.llm_handle, ctypes.byref(rkllm_input), ctypes.byref(rkllm_infer_params), c_userdata)
+        if ret != 0:
+            raise RuntimeError(f"rkllm_run failed with error code {ret}")
+        return ret
+
+    def run_async(self, rkllm_input: RKLLMInput, rkllm_infer_params: RKLLMInferParam, userdata=None) -> int:
+        """Runs an LLM inference task asynchronously."""
+        if userdata is not None:
+            # Store the userdata object to keep it alive during the call
+            self._userdata_ref = userdata
+            c_userdata = ctypes.cast(ctypes.pointer(ctypes.py_object(userdata)), ctypes.c_void_p)
+        else:
+            c_userdata = None
+        ret = self.lib.rkllm_run_async(self.llm_handle, ctypes.byref(rkllm_input), ctypes.byref(rkllm_infer_params), c_userdata)
+        if ret != 0:
+            raise RuntimeError(f"rkllm_run_async failed with error code {ret}")
+        return ret
+
+    def abort(self) -> int:
+        """Aborts an ongoing LLM task."""
+        ret = self.lib.rkllm_abort(self.llm_handle)
+        if ret != 0:
+            raise RuntimeError(f"rkllm_abort failed with error code {ret}")
+        return ret
+
+    def is_running(self) -> bool:
+        """Checks if an LLM task is currently running. Returns True if running."""
+        # The C API returns 0 if running, non-zero otherwise.
+        # This is a bit counter-intuitive for a boolean "is_running".
+        return self.lib.rkllm_is_running(self.llm_handle) == 0
+
+    def clear_kv_cache(self, keep_system_prompt: bool, start_pos: list = None, end_pos: list = None) -> int:
+        """
+        清除键值缓存
+        
+        此函数用于清除部分或全部KV缓存。
+        
+        参数：
+        - keep_system_prompt: 是否在缓存中保留系统提示（True保留，False清除）
+                              如果提供了特定范围[start_pos, end_pos)，此标志将被忽略
+        - start_pos: 要清除的KV缓存范围的起始位置数组（包含），每个批次一个
+        - end_pos: 要清除的KV缓存范围的结束位置数组（不包含），每个批次一个
+                   如果start_pos和end_pos都设置为None，将清除整个缓存，keep_system_prompt将生效
+                   如果start_pos[i] < end_pos[i]，只有指定的范围会被清除，keep_system_prompt将被忽略
+        
+        注意：start_pos或end_pos只有在keep_history == 0且生成已通过在回调中返回1暂停时才有效
+        
+        返回：0表示缓存清除成功，非零表示失败
+        """
+        # 准备C数组参数
+        c_start_pos = None
+        c_end_pos = None
+        
+        if start_pos is not None and end_pos is not None:
+            if len(start_pos) != len(end_pos):
+                raise ValueError("start_pos和end_pos数组长度必须相同")
+            
+            # 创建C数组
+            c_start_pos = (ctypes.c_int * len(start_pos))(*start_pos)
+            c_end_pos = (ctypes.c_int * len(end_pos))(*end_pos)
+        
+        ret = self.lib.rkllm_clear_kv_cache(
+            self.llm_handle, 
+            ctypes.c_int(1 if keep_system_prompt else 0),
+            c_start_pos,
+            c_end_pos
+        )
+        if ret != 0:
+            raise RuntimeError(f"rkllm_clear_kv_cache失败，错误代码：{ret}")
+        return ret
+
+    def set_chat_template(self, system_prompt: str, prompt_prefix: str, prompt_postfix: str) -> int:
+        """Sets the chat template for the LLM."""
+        c_system = system_prompt.encode('utf-8') if system_prompt else b""
+        c_prefix = prompt_prefix.encode('utf-8') if prompt_prefix else b""
+        c_postfix = prompt_postfix.encode('utf-8') if prompt_postfix else b""
+        
+        ret = self.lib.rkllm_set_chat_template(self.llm_handle, c_system, c_prefix, c_postfix)
+        if ret != 0:
+            raise RuntimeError(f"rkllm_set_chat_template failed with error code {ret}")
+        return ret
+
+    def get_kv_cache_size(self, n_batch: int) -> list:
+        """
+        获取给定LLM句柄的键值缓存当前大小
+        
+        此函数返回当前存储在模型KV缓存中的位置总数。
+        
+        参数：
+        - n_batch: 批次数量，用于确定返回数组的大小
+        
+        返回：
+        - list: 每个批次的缓存大小列表
+        """
+        # 预分配数组以存储每个批次的缓存大小
+        cache_sizes = (ctypes.c_int * n_batch)()
+        
+        ret = self.lib.rkllm_get_kv_cache_size(self.llm_handle, cache_sizes)
+        if ret != 0:
+            raise RuntimeError(f"rkllm_get_kv_cache_size失败，错误代码：{ret}")
+        
+        # 转换为Python列表
+        return [cache_sizes[i] for i in range(n_batch)]
+
+    def set_function_tools(self, system_prompt: str, tools: str, tool_response_str: str) -> int:
+        """
+        为LLM设置函数调用配置，包括系统提示、工具定义和工具响应token
+        
+        参数：
+        - system_prompt: 定义语言模型上下文或行为的系统提示
+        - tools: JSON格式的字符串，定义可用的函数，包括它们的名称、描述和参数
+        - tool_response_str: 用于识别对话中函数调用结果的唯一标签。它作为标记标签，
+                            允许分词器将工具输出与正常对话轮次分开识别
+        
+        返回：0表示配置设置成功，非零表示错误
+        """
+        c_system = system_prompt.encode('utf-8') if system_prompt else b""
+        c_tools = tools.encode('utf-8') if tools else b""
+        c_tool_response = tool_response_str.encode('utf-8') if tool_response_str else b""
+        
+        ret = self.lib.rkllm_set_function_tools(self.llm_handle, c_system, c_tools, c_tool_response)
+        if ret != 0:
+            raise RuntimeError(f"rkllm_set_function_tools失败，错误代码：{ret}")
+        return ret
+
+    def set_cross_attn_params(self, cross_attn_params: RKLLMCrossAttnParam) -> int:
+        """
+        为LLM解码器设置交叉注意力参数
+        
+        参数：
+        - cross_attn_params: 包含用于交叉注意力的编码器相关输入数据的结构体
+                            （详见RKLLMCrossAttnParam说明）
+        
+        返回：0表示参数设置成功，非零表示错误
+        """
+        ret = self.lib.rkllm_set_cross_attn_params(self.llm_handle, ctypes.byref(cross_attn_params))
+        if ret != 0:
+            raise RuntimeError(f"rkllm_set_cross_attn_params失败，错误代码：{ret}")
+        return ret
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        self.destroy()
+
+    def __del__(self):
+        self.destroy() # Ensure resources are freed if object is garbage collected
+
+# --- Example Usage (Illustrative) ---
+if __name__ == "__main__":
+    # This is a placeholder for how you might use it.
+    # You'll need a valid .rkllm model and librkllmrt.so in your path.
+
+    # Global list to store results from callback for demonstration
+    results_buffer = []
+
+    def my_python_callback(result_ptr, userdata_ptr, state_enum):
+        """
+        回调函数，由C库调用来处理LLM结果
+        
+        参数：
+        - result_ptr: 指向LLM结果的指针
+        - userdata_ptr: 用户数据指针
+        - state_enum: LLM调用状态枚举值
+        
+        返回：
+        - 0: 继续推理
+        - 1: 暂停推理
+        """
+        global results_buffer
+        state = LLMCallState(state_enum)
+        result = result_ptr.contents
+
+        current_text = ""
+        if result.text: # 检查char_p是否不为NULL
+            current_text = result.text.decode('utf-8', errors='ignore')
+        
+        print(f"回调: State={state.name}, TokenID={result.token_id}, Text='{current_text}'")
+        
+        # 显示性能统计信息
+        if result.perf.prefill_tokens > 0 or result.perf.generate_tokens > 0:
+            print(f"  性能统计: 预填充={result.perf.prefill_tokens}tokens/{result.perf.prefill_time_ms:.1f}ms, "
+                  f"生成={result.perf.generate_tokens}tokens/{result.perf.generate_time_ms:.1f}ms, "
+                  f"内存={result.perf.memory_usage_mb:.1f}MB")
+        
+        results_buffer.append(current_text)
+
+        if state == LLMCallState.RKLLM_RUN_FINISH:
+            print("推理完成。")
+        elif state == LLMCallState.RKLLM_RUN_ERROR:
+            print("推理错误。")
+        
+        # 返回0继续推理，返回1暂停推理
+        return 0
+
+    # --- Attempt to use the wrapper ---
+    try:
+        print("Initializing RKLLMRuntime...")
+        # Adjust library_path if librkllmrt.so is not in default search paths
+        # e.g., library_path="./path/to/librkllmrt.so"
+        rk_llm = RKLLMRuntime() 
+
+        print("Creating default parameters...")
+        params = rk_llm.create_default_param()
+
+        # --- Configure parameters ---
+        # THIS IS CRITICAL: model_path must point to an actual .rkllm file
+        # For this example to run, you need a model file.
+        # Let's assume a dummy path for now, this will fail at init if not valid.
+        model_file = "dummy_model.rkllm" 
+        if not os.path.exists(model_file):
+            print(f"Warning: Model file '{model_file}' does not exist. Init will likely fail.")
+            # Create a dummy file for the example to proceed further, though init will still fail
+            # with a real library unless it's a valid model.
+            with open(model_file, "w") as f:
+                f.write("dummy content")
+
+        params.model_path = model_file.encode('utf-8')
+        params.max_context_len = 512
+        params.max_new_tokens = 128
+        params.top_k = 1 # Greedy
+        params.temperature = 0.7
+        params.repeat_penalty = 1.1
+        # ... set other params as needed
+
+        print(f"Initializing LLM with model: {params.model_path.decode()}...")
+        # This will likely fail if dummy_model.rkllm is not a valid model recognized by the library
+        try:
+            rk_llm.init(params, my_python_callback)
+            print("LLM Initialized.")
+        except RuntimeError as e:
+            print(f"Error during LLM initialization: {e}")
+            print("This is expected if 'dummy_model.rkllm' is not a valid model.")
+            print("Replace 'dummy_model.rkllm' with a real model path to test further.")
+            exit()
+
+
+        # --- Prepare input ---
+        print("准备输入...")
+        rk_input = RKLLMInput()
+        rk_input.role = b"user"  # 设置角色为用户输入
+        rk_input.enable_thinking = False  # 禁用思考模式（适用于Qwen3模型）
+        rk_input.input_type = RKLLMInputType.RKLLM_INPUT_PROMPT
+        
+        prompt_text = "将以下英文文本翻译成中文：'Hello, world!'"
+        c_prompt = prompt_text.encode('utf-8')
+        rk_input._union_data.prompt_input = c_prompt # 直接访问联合体成员
+
+        # --- Prepare inference parameters ---
+        print("Preparing inference parameters...")
+        infer_params = RKLLMInferParam()
+        infer_params.mode = RKLLMInferMode.RKLLM_INFER_GENERATE
+        infer_params.keep_history = 1 # True
+        # infer_params.lora_params = None # or set up RKLLMLoraParam if using LoRA
+        # infer_params.prompt_cache_params = None # or set up RKLLMPromptCacheParam
+
+        # --- Run inference ---
+        print(f"Running inference with prompt: '{prompt_text}'")
+        results_buffer.clear()
+        try:
+            rk_llm.run(rk_input, infer_params) # Userdata is None by default
+            print("\n--- Full Response ---")
+            print("".join(results_buffer))
+            print("---------------------\n")
+        except RuntimeError as e:
+            print(f"Error during LLM run: {e}")
+
+
+        # --- Example: Set chat template (if model supports it) ---
+        # print("Setting chat template...")
+        # try:
+        #     rk_llm.set_chat_template("You are a helpful assistant.", "<user>: ", "<assistant>: ")
+        #     print("Chat template set.")
+        # except RuntimeError as e:
+        #     print(f"Error setting chat template: {e}")
+
+        # --- Example: Clear KV Cache ---
+        # print("Clearing KV cache (keeping system prompt if any)...")
+        # try:
+        #     rk_llm.clear_kv_cache(keep_system_prompt=True)
+        #     print("KV cache cleared.")
+        # except RuntimeError as e:
+        #     print(f"Error clearing KV cache: {e}")
+
+        # --- 示例：获取KV缓存大小 ---
+        # print("获取KV缓存大小...")
+        # try:
+        #     cache_sizes = rk_llm.get_kv_cache_size(n_batch=1)  # 假设批次大小为1
+        #     print(f"当前KV缓存大小: {cache_sizes}")
+        # except RuntimeError as e:
+        #     print(f"获取KV缓存大小错误: {e}")
+
+        # --- 示例：设置函数工具 ---
+        # print("设置函数调用工具...")
+        # try:
+        #     system_prompt = "你是一个有用的助手，可以调用提供的函��来帮助用户。"
+        #     tools = '''[{
+        #         "name": "get_weather",
+        #         "description": "获取指定城市的天气信息",
+        #         "parameters": {
+        #             "type": "object",
+        #             "properties": {
+        #                 "city": {"type": "string", "description": "城市名称"}
+        #             },
+        #             "required": ["city"]
+        #         }
+        #     }]'''
+        #     tool_response_str = "<tool_response>"
+        #     rk_llm.set_function_tools(system_prompt, tools, tool_response_str)
+        #     print("函数工具设置成功。")
+        # except RuntimeError as e:
+        #     print(f"设置函数工具错误: {e}")
+
+        # --- 示例：清除KV缓存（带范围参数） ---
+        # print("使用范围参数清除KV缓存...")
+        # try:
+        #     # 清除位置10到20的缓存
+        #     start_positions = [10]  # 批次0的起始位置
+        #     end_positions = [20]    # 批次0的结束位置
+        #     rk_llm.clear_kv_cache(keep_system_prompt=True, start_pos=start_positions, end_pos=end_positions)
+        #     print("范围KV缓存清除完成。")
+        # except RuntimeError as e:
+        #     print(f"清除范围KV缓存错误: {e}")
+        
+    except OSError as e:
+        print(f"OSError: {e}. Could not load the RKLLM library.")
+        print("Please ensure 'librkllmrt.so' is in your LD_LIBRARY_PATH or provide the full path.")
+    except Exception as e:
+        print(f"An unexpected error occurred: {e}")
+    finally:
+        if 'rk_llm' in locals() and rk_llm.llm_handle and rk_llm.llm_handle.value:
+            print("Destroying LLM instance...")
+            rk_llm.destroy()
+            print("LLM instance destroyed.")
+        if os.path.exists(model_file) and model_file == "dummy_model.rkllm":
+             os.remove(model_file) # Clean up dummy file
+
+    print("Example finished.")

rknn_quickconvert.py

@@ -0,0 +1,58 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+import os
+import sys
+from rknn.api import RKNN
+import argparse
+
+def quick_convert(onnx_model_path):
+    rknn = RKNN(verbose=True)
+    rknn.config(quantized_algorithm='normal', quantized_method='channel', target_platform='rk3588', optimization_level=3, model_pruning=True)
+    ret = rknn.load_onnx(model=onnx_model_path)
+    if ret != 0:
+        print('Load model failed!')
+        exit(ret)
+    rknn.build(do_quantization=False, dataset=None, rknn_batch_size=None)
+    rknn_model_path = onnx_model_path.replace(".onnx", ".rknn")
+    ret = rknn.export_rknn(rknn_model_path)
+    if ret != 0:
+        print('Export RKNN model failed!')
+        exit(ret)
+    print(f"RKNN model exported to {rknn_model_path}")
+    
+def compile_only(onnx_model_path):
+    from rknn.api.rknn_compiler import RKNNCompiler, RKNNConfig, RKNNNormalize
+    from rknn.api.rknn_platform import support_soc_npu_target
+    from pprint import pprint
+
+    pprint(support_soc_npu_target)
+
+    RKNNCompiler.build(
+        onnx_model_path,
+        RKNNConfig(
+            target="v2",  
+            request_type="float16",
+            optimize_options="compress=0, conv_eltwise_activation_fuse=1, global_fuse=1, multi-core-model-mode=1, output_optimize=1, layout_match=1, enable_argb_group=0, pipeline_fuse=1, enable_flash_attention=0",
+            verbose_level=4,
+        ),
+        RKNNNormalize(
+            channel_means=[[0, 0, 0]],
+            channel_stds=[[1, 1, 1]],
+            channel_orders=[[0, 1, 2]],  # not tested !!!
+        ),
+        "out.rknn",
+    )
+
+# "Usage: python rknn_quickconvert.py <onnx_model_path> [-c/--compile-only]"
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("onnx_model_path", type=str, help="Path to the ONNX model file")
+    parser.add_argument("-c", "--compile-only", action="store_true", help="Compile the model only")
+    args = parser.parse_args()
+
+    onnx_model_path = args.onnx_model_path
+    if args.compile_only:
+        compile_only(onnx_model_path)
+    else:
+        quick_convert(onnx_model_path)

run_rkllm.py

@@ -0,0 +1,226 @@
+import faulthandler
+faulthandler.enable()
+import sys
+import os
+os.environ["RKLLM_LOG_LEVEL"] = "1"
+import ctypes
+import argparse
+import cv2
+import numpy as np
+import ztu_somemodelruntime_rknnlite2 as ort
+from rkllm_binding import (
+    RKLLMRuntime,
+    RKLLMParam,
+    RKLLMInput,
+    RKLLMInferParam,
+    LLMCallState,
+    RKLLMInputType,
+    RKLLMInferMode,
+    RKLLMResult
+)
+
+# Constants
+IMAGE_HEIGHT = 448
+IMAGE_WIDTH = 448
+
+def expand2square(img, background_color):
+    """
+    Expand the image into a square and fill it with the specified background color.
+    """
+    height, width, _ = img.shape
+    if width == height:
+        return img.copy()
+
+    size = max(width, height)
+    square_img = np.full((size, size, 3), background_color, dtype=np.uint8)
+
+    x_offset = (size - width) // 2
+    y_offset = (size - height) // 2
+
+    square_img[y_offset:y_offset+height, x_offset:x_offset+width] = img
+    return square_img
+
+def llm_callback(result_ptr, userdata_ptr, state_enum):
+    """
+    Callback function to handle LLM results.
+    """
+    state = LLMCallState(state_enum)
+    result = result_ptr.contents
+
+    if state == LLMCallState.RKLLM_RUN_NORMAL:
+        if result.text:
+            print(result.text.decode('utf-8', errors='ignore'), end='', flush=True)
+    elif state == LLMCallState.RKLLM_RUN_FINISH:
+        print("\n", flush=True)
+    elif state == LLMCallState.RKLLM_RUN_ERROR:
+        print("\nrun error", flush=True)
+    
+    return 0
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Run RKLLM visual language model inference based on the C++ example."
+    )
+    parser.add_argument("image_path", type=str, help="Path to the input image.")
+    parser.add_argument("encoder_model_path", type=str, help="Path to the ONNX vision encoder model.")
+    parser.add_argument("llm_model_path", type=str, help="Path to the .rkllm language model.")
+    parser.add_argument("max_new_tokens", type=int, help="Maximum number of new tokens to generate.")
+    parser.add_argument("max_context_len", type=int, help="Maximum context length.")
+    # The rknn_core_num is not directly used by onnxruntime in the same way,
+    # but we keep it for API consistency with the C++ example.
+    # ONNX Runtime will manage its own threading and execution providers.
+    parser.add_argument("rknn_core_num", type=int, help="Core number for RKNN (informational for this script).")
+
+    args = parser.parse_args()
+
+    # --- 1. Initialize Image Encoder (ONNX Runtime) ---
+    print("Initializing ONNX Runtime for vision encoder...")
+    try:
+        ort_session = ort.InferenceSession(args.encoder_model_path)
+    except Exception as e:
+        print(f"Failed to load ONNX model: {e}")
+        sys.exit(1)
+    print("Vision encoder loaded successfully.")
+    
+    input_name = ort_session.get_inputs()[0].name
+    output_name = ort_session.get_outputs()[0].name
+    print(f"ONNX Input: {input_name}, ONNX Output: {output_name}")
+
+    # --- 2. Initialize LLM ---
+    print("Initializing RKLLM Runtime...")
+    rk_llm = RKLLMRuntime()
+    param = rk_llm.create_default_param()
+
+    param.model_path = args.llm_model_path.encode('utf-8')
+    param.top_k = 1
+    param.max_new_tokens = args.max_new_tokens
+    param.max_context_len = args.max_context_len
+    param.skip_special_token = True
+    param.img_start = b"<|vision_start|>"
+    param.img_end = b"<|vision_end|>"
+    param.img_content = b"<|image_pad|>"
+    param.extend_param.base_domain_id = 1
+
+    try:
+        rk_llm.init(param, llm_callback)
+        print("RKLLM initialized successfully.")
+    except RuntimeError as e:
+        print(f"RKLLM init failed: {e}")
+        sys.exit(1)
+
+    # --- 3. Image Preprocessing ---
+    print("Preprocessing image...")
+    img = cv2.imread(args.image_path)
+    if img is None:
+        print(f"Failed to read image from {args.image_path}")
+        sys.exit(1)
+        
+    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+
+    background_color = (127.5, 127.5, 127.5) # As per C++ example
+    square_img = expand2square(img, background_color)
+    resized_img = cv2.resize(square_img, (IMAGE_WIDTH, IMAGE_HEIGHT), interpolation=cv2.INTER_LINEAR)
+    
+    # Normalize and prepare for ONNX model
+    input_tensor = resized_img.astype(np.float32)
+    # Normalize using preprocessor config values
+    input_tensor = (input_tensor / 255.0 - np.array([0.48145466, 0.4578275, 0.40821073])) / np.array([0.26862954, 0.26130258, 0.27577711])
+    # Convert to NCHW format
+    input_tensor = np.transpose(input_tensor, (2, 0, 1))  # HWC -> CHW
+    input_tensor = np.expand_dims(input_tensor, axis=0)  # Add batch dimension -> (1, 3, 392, 392)
+
+    # --- 4. Run Image Encoder ---
+    print("Running vision encoder...")
+    try:
+        img_vec_output = ort_session.run([output_name], {input_name: input_tensor.astype(np.float32)})[0]
+        # The output from C++ is a flat float array. Let's flatten the ONNX output.
+        img_vec = img_vec_output.flatten().astype(np.float32)
+
+    except Exception as e:
+        print(f"Failed to run vision encoder inference: {e}")
+        rk_llm.destroy()
+        sys.exit(1)
+    
+    print("Image encoded successfully.")
+
+    # --- 5. Interactive Chat Loop ---
+    rkllm_infer_params = RKLLMInferParam()
+    rkllm_infer_params.mode = RKLLMInferMode.RKLLM_INFER_GENERATE
+    rkllm_infer_params.keep_history = 0
+
+    # Set chat template
+    rk_llm.set_chat_template(
+        system_prompt="<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n",
+        prompt_prefix="<|im_start|>user\n",
+        prompt_postfix="<|im_end|>\n<|im_start|>assistant\n"
+    )
+
+    pre_input = [
+        "Picture 1: <image> What is in the image?",
+        "Picture 1: <image> 这张图片中有什么？"
+    ]
+    print("\n**********************可输入以下问题对应序号获取回答/或自定义输入********************\n")
+    for i, p in enumerate(pre_input):
+        print(f"[{i}] {p}")
+    print("\n*************************************************************************\n")
+
+    try:
+        while True:
+            print("\nuser: ", end="", flush=True)
+            input_str = sys.stdin.readline().strip()
+
+            if not input_str:
+                continue
+            if input_str == "exit":
+                break
+            if input_str == "clear":
+                try:
+                    rk_llm.clear_kv_cache(keep_system_prompt=True)
+                    print("KV cache cleared.")
+                except RuntimeError as e:
+                    print(f"Failed to clear KV cache: {e}")
+                continue
+
+            try:
+                idx = int(input_str)
+                if 0 <= idx < len(pre_input):
+                    input_str = pre_input[idx]
+                    print(input_str)
+            except (ValueError, IndexError):
+                pass # Use the raw string if not a valid index
+
+            rkllm_input = RKLLMInput()
+            rkllm_input.role = b"user"
+            
+            print("robot: ", end="", flush=True)
+
+            if "<image>" in input_str:
+                rkllm_input.input_type = RKLLMInputType.RKLLM_INPUT_MULTIMODAL
+                
+                # Setup multimodal input
+                rkllm_input.multimodal_input.prompt = input_str.encode('utf-8')
+                rkllm_input.multimodal_input.image_embed = img_vec.ctypes.data_as(ctypes.POINTER(ctypes.c_float))
+                rkllm_input.multimodal_input.n_image_tokens = img_vec_output.shape[0]
+                print("n_image_tokens: ", rkllm_input.multimodal_input.n_image_tokens)
+                rkllm_input.multimodal_input.n_image = 1
+                rkllm_input.multimodal_input.image_height = IMAGE_HEIGHT
+                rkllm_input.multimodal_input.image_width = IMAGE_WIDTH
+            else:
+                rkllm_input.input_type = RKLLMInputType.RKLLM_INPUT_PROMPT
+                rkllm_input.prompt_input = input_str.encode('utf-8')
+
+            try:
+                rk_llm.run(rkllm_input, rkllm_infer_params)
+            except RuntimeError as e:
+                print(f"\nError during rkllm_run: {e}")
+
+    except KeyboardInterrupt:
+        print("\nExiting...")
+    finally:
+        print("Releasing resources...")
+        rk_llm.destroy()
+        print("RKLLM instance destroyed.")
+
+if __name__ == "__main__":
+    main()
+

ztu_somemodelruntime_rknnlite2.py

@@ -0,0 +1,569 @@
+# 模块级常量和函数
+from rknnlite.api import RKNNLite
+import numpy as np
+import os
+import warnings
+import logging
+from typing import List, Dict, Union, Optional
+
+try:
+    import onnxruntime as ort
+    HAS_ORT = True
+except ImportError:
+    HAS_ORT = False
+    warnings.warn("onnxruntime未安装,只能使用RKNN后端", ImportWarning)
+
+# 配置日志
+logger = logging.getLogger("somemodelruntime_rknnlite2")
+logger.setLevel(logging.ERROR)  # 默认只输出错误信息
+if not logger.handlers:
+    handler = logging.StreamHandler()
+    handler.setFormatter(logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s'))
+    logger.addHandler(handler)
+
+# ONNX Runtime日志级别到Python logging级别的映射
+_LOGGING_LEVEL_MAP = {
+    0: logging.DEBUG,    # Verbose
+    1: logging.INFO,     # Info
+    2: logging.WARNING,  # Warning
+    3: logging.ERROR,    # Error
+    4: logging.CRITICAL  # Fatal
+}
+
+# 检查环境变量中的日志级别设置
+try:
+    env_log_level = os.getenv('ZTU_MODELRT_RKNNL2_LOG_LEVEL')
+    if env_log_level is not None:
+        log_level = int(env_log_level)
+        if log_level in _LOGGING_LEVEL_MAP:
+            logger.setLevel(_LOGGING_LEVEL_MAP[log_level])
+            logger.info(f"从环境变量设置日志级别: {log_level}")
+        else:
+            logger.warning(f"环境变量ZTU_MODELRT_RKNNL2_LOG_LEVEL的值无效: {log_level}, 应该是0-4之间的整数")
+except ValueError:
+    logger.warning(f"环境变量ZTU_MODELRT_RKNNL2_LOG_LEVEL的值无效: {env_log_level}, 应该是0-4之间的整数")
+
+
+def set_default_logger_severity(level: int) -> None:
+    """
+    Sets the default logging severity. 0:Verbose, 1:Info, 2:Warning, 3:Error, 4:Fatal
+    
+    Args:
+        level: 日志级别(0-4)
+    """
+    if level not in _LOGGING_LEVEL_MAP:
+        raise ValueError(f"无效的日志级别: {level}, 应该是0-4之间的整数")
+    logger.setLevel(_LOGGING_LEVEL_MAP[level])
+
+def set_default_logger_verbosity(level: int) -> None:
+    """
+    Sets the default logging verbosity level. To activate the verbose log, 
+    you need to set the default logging severity to 0:Verbose level.
+    
+    Args:
+        level: 日志级别(0-4)
+    """
+    set_default_logger_severity(level)
+
+# RKNN tensor type到numpy dtype的映射
+RKNN_DTYPE_MAP = {
+    0: np.float32,  # RKNN_TENSOR_FLOAT32
+    1: np.float16,  # RKNN_TENSOR_FLOAT16
+    2: np.int8,     # RKNN_TENSOR_INT8
+    3: np.uint8,    # RKNN_TENSOR_UINT8
+    4: np.int16,    # RKNN_TENSOR_INT16
+    5: np.uint16,   # RKNN_TENSOR_UINT16
+    6: np.int32,    # RKNN_TENSOR_INT32
+    7: np.uint32,   # RKNN_TENSOR_UINT32
+    8: np.int64,    # RKNN_TENSOR_INT64
+    9: bool,        # RKNN_TENSOR_BOOL
+    10: np.int8,    # RKNN_TENSOR_INT4 (用int8表示)
+}
+
+def get_available_providers() -> List[str]:
+    """
+    获取可用的设备提供者列表(为保持接口兼容性的占位函数)
+    
+    Returns:
+        list: 可用的设备提供者列表,总是返回["CPUExecutionProvider", "somemodelruntime_rknnlite2_ExecutionProvider"]
+    """
+    return ["CPUExecutionProvider", "somemodelruntime_rknnlite2_ExecutionProvider"]
+
+
+def get_device() -> str:
+    """
+    获取当前设备
+
+    Returns:
+        str: 当前设备
+    """
+    return "RKNN2"
+
+def get_version_info() -> Dict[str, str]:
+    """
+    获取版本信息
+    
+    Returns:
+        dict: 包含API和驱动版本信息的字典
+    """
+    runtime = RKNNLite()
+    version = runtime.get_sdk_version()
+    return {
+        "api_version": version.split('\n')[2].split(': ')[1].split(' ')[0],
+        "driver_version": version.split('\n')[3].split(': ')[1]
+    }
+
+class IOTensor:
+    """输入/输出张量的信息封装类"""
+    def __init__(self, name, shape, type=None):
+        self.name = name.decode() if isinstance(name, bytes) else name
+        self.shape = shape
+        self.type = type
+
+    def __str__(self):
+        return f"IOTensor(name='{self.name}', shape={self.shape}, type={self.type})"
+
+class SessionOptions:
+    """会话选项类"""
+    def __init__(self):
+        self.enable_profiling = False  # 是否使用性能分析
+        self.intra_op_num_threads = 1  # 设置RKNN的线程数, 对应rknn的core_mask
+        self.log_severity_level = -1 # 另一个设置日志级别的参数
+        self.log_verbosity_level = -1 # 另一个设置日志级别的参数
+
+
+class InferenceSession:
+    """
+    RKNNLite运行时封装类,API风格类似ONNX Runtime
+    """
+
+    def __new__(cls, model_path: str, sess_options: Optional[SessionOptions] = None, **kwargs):
+        processed_path = InferenceSession._process_model_path(model_path, sess_options)
+        if isinstance(processed_path, str) and processed_path.lower().endswith('.onnx'):
+            logger.info("使用ONNX Runtime加载模型")
+            if not HAS_ORT:
+                raise RuntimeError("未安装onnxruntime,无法加载ONNX模型")
+            return ort.InferenceSession(processed_path, sess_options=sess_options, **kwargs)
+        else:
+            # 如果不是 ONNX 模型，则调用父类的 __new__ 创建 InferenceSession 实例
+            instance = super().__new__(cls)
+            # 保存处理后的路径
+            instance._processed_path = processed_path
+            return instance
+
+    def __init__(self, model_path: str, sess_options: Optional[SessionOptions] = None, **kwargs):
+        """
+        初始化运行时并加载模型
+        
+        Args:
+            model_path: 模型文件路径(.rknn或.onnx)
+            sess_options: 会话选项
+            **kwargs: 其他初始化参数
+        """
+        options = sess_options or SessionOptions()
+
+        # 只在未设置环境变量时使用SessionOptions中的日志级别
+        if os.getenv('ZTU_MODELRT_RKNNL2_LOG_LEVEL') is None:
+            if options.log_severity_level != -1:
+                set_default_logger_severity(options.log_severity_level)
+            if options.log_verbosity_level != -1:
+                set_default_logger_verbosity(options.log_verbosity_level)
+            
+        # 使用__new__中处理好的路径
+        model_path = getattr(self, '_processed_path', model_path)
+        if isinstance(model_path, str) and model_path.lower().endswith('.onnx'):
+            # 避免重复加载 ONNX 模型
+            return
+
+        # ... 现有的 RKNN 模型加载和初始化代码 ...
+        self.model_path = model_path
+        if not os.path.exists(self.model_path):
+            logger.error(f"模型文件不存在: {self.model_path}")
+            raise FileNotFoundError(f"模型文件不存在: {self.model_path}")
+
+        self.runtime = RKNNLite(verbose=options.enable_profiling)
+
+        logger.debug(f"正在加载模型: {self.model_path}")
+        ret = self.runtime.load_rknn(self.model_path)
+        if ret != 0:
+            logger.error(f"加载RKNN模型失败: {self.model_path}")
+            raise RuntimeError(f'加载RKNN模型失败: {self.model_path}')
+        logger.debug("模型加载成功")
+
+
+        if options.intra_op_num_threads == 1:
+            core_mask = RKNNLite.NPU_CORE_AUTO
+        elif options.intra_op_num_threads == 2:
+            core_mask = RKNNLite.NPU_CORE_0_1
+        elif options.intra_op_num_threads == 3:
+            core_mask = RKNNLite.NPU_CORE_0_1_2
+        else:
+            raise ValueError(f"intra_op_num_threads的值无效: {options.intra_op_num_threads}, 只能是1,2或3")
+
+        logger.debug("正在初始化运行时环境")
+        ret = self.runtime.init_runtime(core_mask=core_mask)
+        if ret != 0:
+            logger.error("初始化运行时环境失败")
+            raise RuntimeError('初始化运行时环境失败')
+        logger.debug("运行时环境初始化成功")
+
+        self._init_io_info()
+        self.options = options
+
+    def get_performance_info(self) -> Dict[str, float]:
+        """
+        获取性能信息
+        
+        Returns:
+            dict: 包含性能信息的字典
+        """
+        if not self.options.perf_debug:
+            raise RuntimeError("性能分析未启用,请在SessionOptions中设置perf_debug=True")
+            
+        perf = self.runtime.rknn_runtime.get_run_perf()
+        return {
+            "run_duration": perf.run_duration / 1000.0  # 转换为毫秒
+        }
+
+    def set_core_mask(self, core_mask: int) -> None:
+        """
+        设置NPU核心使用模式
+        
+        Args:
+            core_mask: NPU核心掩码,使用NPU_CORE_*常量
+        """
+        ret = self.runtime.rknn_runtime.set_core_mask(core_mask)
+        if ret != 0:
+            raise RuntimeError("设置NPU核心模式失败")
+
+    @staticmethod
+    def _process_model_path(model_path, sess_options):
+        """
+        处理模型路径,支持.onnx和.rknn文件
+        
+        Args:
+            model_path: 模型文件路径
+        """
+        # 如果是ONNX文件,检查是否需要自动加载RKNN
+        if model_path.lower().endswith('.onnx'):
+            logger.info("检测到ONNX模型文件")
+            
+            # 获取需要跳过自动加载的模型列表
+            skip_models = os.getenv('ZTU_MODELRT_RKNNL2_SKIP', '').strip()
+            if skip_models:
+                skip_list = [m.strip() for m in skip_models.split(',')]
+                # 获取模型文件名(不含路径)用于匹配
+                model_name = os.path.basename(model_path)
+                if model_name.lower() in [m.lower() for m in skip_list]:
+                    logger.info(f"模型{model_name}在跳过列表中,将使用ONNX Runtime")
+                    return model_path
+            
+            # 构造RKNN文件路径
+            rknn_path = os.path.splitext(model_path)[0] + '.rknn'
+            if os.path.exists(rknn_path):
+                logger.info(f"找到对应的RKNN模型,将使用RKNN: {rknn_path}")
+                return rknn_path
+            else:
+                logger.info("未找到对应的RKNN模型,将使用ONNX Runtime")
+                return model_path
+            
+        return model_path
+        
+    def _convert_nhwc_to_nchw(self, shape):
+        """将NHWC格式的shape转换为NCHW格式"""
+        if len(shape) == 4:
+            # NHWC -> NCHW
+            n, h, w, c = shape
+            return [n, c, h, w]
+        return shape
+        
+    def _init_io_info(self):
+        """初始化模型的输入输出信息"""
+        runtime = self.runtime.rknn_runtime
+        
+        # 获取输入输出数量
+        n_input, n_output = runtime.get_in_out_num()
+        
+        # 获取输入信息
+        self.input_tensors = []
+        for i in range(n_input):
+            attr = runtime.get_tensor_attr(i)
+            shape = [attr.dims[j] for j in range(attr.n_dims)]
+            # 对四维输入进行NHWC到NCHW的转换
+            shape = self._convert_nhwc_to_nchw(shape)
+            # 获取dtype
+            dtype = RKNN_DTYPE_MAP.get(attr.type, None)
+            tensor = IOTensor(attr.name, shape, dtype)
+            self.input_tensors.append(tensor)
+            
+        # 获取输出信息
+        self.output_tensors = []
+        for i in range(n_output):
+            attr = runtime.get_tensor_attr(i, is_output=True)
+            shape = runtime.get_output_shape(i)
+            # 获取dtype
+            dtype = RKNN_DTYPE_MAP.get(attr.type, None)
+            tensor = IOTensor(attr.name, shape, dtype)
+            self.output_tensors.append(tensor)
+        
+    def get_inputs(self):
+        """
+        获取模型输入信息
+        
+        Returns:
+            list: 包含输入信息的列表
+        """
+        return self.input_tensors
+        
+    def get_outputs(self):
+        """
+        获取模型输出信息
+        
+        Returns:
+            list: 包含输出信息的列表
+        """
+        return self.output_tensors
+        
+    def run(self, output_names=None, input_feed=None, data_format="nchw", **kwargs):
+        """
+        执行模型推理
+        
+        Args:
+            output_names: 输出节点名称列表,指定需要返回哪些输出
+            input_feed: 输入数据字典或列表
+            data_format: 输入数据格式,"nchw"或"nhwc"
+            **kwargs: 其他运行时参数
+            
+        Returns:
+            list: 模型输出结果列表,如果指定了output_names则只返回指定的输出
+        """
+        if input_feed is None:
+            logger.error("input_feed不能为None")
+            raise ValueError("input_feed不能为None")
+            
+        # 准备输入数据
+        if isinstance(input_feed, dict):
+            # 如果是字典,按照模型输入顺序排列
+            inputs = []
+            input_map = {tensor.name: i for i, tensor in enumerate(self.input_tensors)}
+            for tensor in self.input_tensors:
+                if tensor.name not in input_feed:
+                    raise ValueError(f"缺少输入: {tensor.name}")
+                inputs.append(input_feed[tensor.name])
+        elif isinstance(input_feed, (list, tuple)):
+            # 如果是列表,确保长度匹配
+            if len(input_feed) != len(self.input_tensors):
+                raise ValueError(f"输入数量不匹配: 期望{len(self.input_tensors)}, 实际{len(input_feed)}")
+            inputs = list(input_feed)
+        else:
+            logger.error("input_feed必须是字典或列表类型")
+            raise ValueError("input_feed必须是字典或列表类型")
+            
+        # 执行推理
+        try:
+            logger.debug("开始执行推理")
+            all_outputs = self.runtime.inference(inputs=inputs, data_format=data_format)
+            
+            # 如果没有指定output_names,返回所有输出
+            if output_names is None:
+                return all_outputs
+                
+            # 获取指定的输出
+            output_map = {tensor.name: i for i, tensor in enumerate(self.output_tensors)}
+            selected_outputs = []
+            for name in output_names:
+                if name not in output_map:
+                    raise ValueError(f"未找到输出节点: {name}")
+                selected_outputs.append(all_outputs[output_map[name]])
+                    
+            return selected_outputs
+            
+        except Exception as e:
+            logger.error(f"推理执行失败: {str(e)}")
+            raise RuntimeError(f"推理执行失败: {str(e)}")
+        
+    def close(self):
+        """
+        关闭会话,释放资源
+        """
+        if self.runtime is not None:
+            logger.info("正在释放运行时资源")
+            self.runtime.release()
+            self.runtime = None
+            
+    def __enter__(self):
+        return self
+        
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        self.close()
+
+    def end_profiling(self) -> Optional[str]:
+        """
+        结束性能分析的存根方法
+        
+        Returns:
+            Optional[str]: None
+        """
+        warnings.warn("end_profiling()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+        return None
+        
+    def get_profiling_start_time_ns(self) -> int:
+        """
+        获取性能分析开始时间的存根方法
+        
+        Returns:
+            int: 0
+        """
+        warnings.warn("get_profiling_start_time_ns()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+        return 0
+        
+    def get_modelmeta(self) -> Dict[str, str]:
+        """
+        获取模型元数据的存根方法
+        
+        Returns:
+            Dict[str, str]: 空字典
+        """
+        warnings.warn("get_modelmeta()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+        return {}
+        
+    def get_session_options(self) -> SessionOptions:
+        """
+        获取会话选项
+        
+        Returns:
+            SessionOptions: 当前会话选项
+        """
+        return self.options
+        
+    def get_providers(self) -> List[str]:
+        """
+        获取当前使用的providers的存根方法
+        
+        Returns:
+            List[str]: ["CPUExecutionProvider"]
+        """
+        warnings.warn("get_providers()是存根方法,始终返回CPUExecutionProvider", RuntimeWarning, stacklevel=2)
+        return ["CPUExecutionProvider"]
+        
+    def get_provider_options(self) -> Dict[str, Dict[str, str]]:
+        """
+        获取provider选项的存根方法
+        
+        Returns:
+            Dict[str, Dict[str, str]]: 空字典
+        """
+        warnings.warn("get_provider_options()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+        return {} 
+
+    def get_session_config(self) -> Dict[str, str]:
+        """
+        获取会话配置的存根方法
+        
+        Returns:
+            Dict[str, str]: 空字典
+        """
+        warnings.warn("get_session_config()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+        return {}
+
+    def get_session_state(self) -> Dict[str, str]:
+        """
+        获取会话状态的存根方法
+        
+        Returns:
+            Dict[str, str]: 空字典
+        """
+        warnings.warn("get_session_state()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+        return {}
+
+    def set_session_config(self, config: Dict[str, str]) -> None:
+        """
+        设置会话配置的存根方法
+        
+        Args:
+            config: 会话配置字典
+        """
+        warnings.warn("set_session_config()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+
+    def get_memory_info(self) -> Dict[str, int]:
+        """
+        获取内存使用信息的存根方法
+        
+        Returns:
+            Dict[str, int]: 空字典
+        """
+        warnings.warn("get_memory_info()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+        return {}
+
+    def set_memory_pattern(self, enable: bool) -> None:
+        """
+        设置内存模式的存根方法
+        
+        Args:
+            enable: 是否启用内存模式
+        """
+        warnings.warn("set_memory_pattern()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+
+    def disable_memory_pattern(self) -> None:
+        """
+        禁用内存模式的存根方法
+        """
+        warnings.warn("disable_memory_pattern()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+
+    def get_optimization_level(self) -> int:
+        """
+        获取优化级别的存根方法
+        
+        Returns:
+            int: 0
+        """
+        warnings.warn("get_optimization_level()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+        return 0
+
+    def set_optimization_level(self, level: int) -> None:
+        """
+        设置优化级别的存根方法
+        
+        Args:
+            level: 优化级别
+        """
+        warnings.warn("set_optimization_level()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+
+    def get_model_metadata(self) -> Dict[str, str]:
+        """
+        获取模型元数据的存根方法(与get_modelmeta不同的接口)
+        
+        Returns:
+            Dict[str, str]: 空字典
+        """
+        warnings.warn("get_model_metadata()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+        return {}
+
+    def get_model_path(self) -> str:
+        """
+        获取模型路径
+        
+        Returns:
+            str: 模型文件路径
+        """
+        return self.model_path
+
+    def get_input_type_info(self) -> List[Dict[str, str]]:
+        """
+        获取输入类型信息的存根方法
+        
+        Returns:
+            List[Dict[str, str]]: 空列表
+        """
+        warnings.warn("get_input_type_info()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+        return []
+
+    def get_output_type_info(self) -> List[Dict[str, str]]:
+        """
+        获取输出类型信息的存根方法
+        
+        Returns:
+            List[Dict[str, str]]: 空列表
+        """
+        warnings.warn("get_output_type_info()是存根方法,不提供实际功能", RuntimeWarning, stacklevel=2)
+        return []