1
数学库
Ktransformers v0.3.1-fastpt 部署 DeepSeek-R1-Q4,推理报错
2025-09-18 10:44:28
173

本机环境: CPU:Intel(R) Xeon(R) Silver 4410Y

DCU:K100_AI

镜像:image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.4.1-ubuntu22.04-dtk25.04-py3.10 Ktransformers:v0.3.1

启动命令:ktransformers/server/main.py --model_path /mnt/model/DeepSeek-R1-GGUF/DeepSeek-R1-Q4/ --gguf_path /mnt/model/DeepSeek-R1-GGUF/DeepSeek-R1-Q4/ --optimize_config_path ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-dcu.yaml --cpu_infer 48 --backend_type=ktransformers --force_think  --chunk_size=256  --max_new_tokens=35678  --max_batch_size=4  --temperature=0.6 --top_p=0.95

模型能够正常启动,但是推理时直接报错,报错信息如下:


for Windows or GPU before ampere or Z100/Z100L or K100, use forward_windows
for Windows or GPU before ampere or Z100/Z100L or K100, use forward_windows
for Windows or GPU before ampere or Z100/Z100L or K100, use forward_windows
for Windows or GPU before ampere or Z100/Z100L or K100, use forward_windows
for Windows or GPU before ampere or Z100/Z100L or K100, use forward_windows
for Windows or GPU before ampere or Z100/Z100L or K100, use forward_windows
for Windows or GPU before ampere or Z100/Z100L or K100, use forward_windows
for Windows or GPU before ampere or Z100/Z100L or K100, use forward_windows
for Windows or GPU before ampere or Z100/Z100L or K100, use forward_windows
INFO:     10.200.9.247:10235 - "POST /v1/chat/completions HTTP/1.1" 500 Internal Server Error
ERROR:    Exception in ASGI application
Traceback (most recent call last):
  File "/usr/local/lib/python3.10/site-packages/ktransformers/server/backend/interfaces/transformers.py", line 227, in prepare_logits_wrapper
    self.model._get_logits_warper(generation_config, device=device)
  File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1729, in __getattr__
    raise AttributeError(f"'{type(self).__name__}' object has no attribute '{name}'")
AttributeError: 'DeepseekV3ForCausalLM' object has no attribute '_get_logits_warper'. Did you mean: '_get_logits_processor'?

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/usr/local/lib/python3.10/site-packages/uvicorn/protocols/http/httptools_impl.py", line 409, in run_asgi
    result = await app(  # type: ignore[func-returns-value]
  File "/usr/local/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
    return await self.app(scope, receive, send)
  File "/usr/local/lib/python3.10/site-packages/fastapi/applications.py", line 1054, in __call__
    await super().__call__(scope, receive, send)
  File "/usr/local/lib/python3.10/site-packages/starlette/applications.py", line 112, in __call__
    await self.middleware_stack(scope, receive, send)
  File "/usr/local/lib/python3.10/site-packages/starlette/middleware/errors.py", line 187, in __call__
    raise exc
  File "/usr/local/lib/python3.10/site-packages/starlette/middleware/errors.py", line 165, in __call__
    await self.app(scope, receive, _send)
  File "/usr/local/lib/python3.10/site-packages/starlette/middleware/cors.py", line 85, in __call__
    await self.app(scope, receive, send)
  File "/usr/local/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
    await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
  File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
    raise exc
  File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
    await app(scope, receive, sender)
  File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 714, in __call__
    await self.middleware_stack(scope, receive, send)
  File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 734, in app
    await route.handle(scope, receive, send)
  File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 288, in handle
    await self.app(scope, receive, send)
  File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 76, in app
    await wrap_app_handling_exceptions(app, request)(scope, receive, send)
  File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
    raise exc
  File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
    await app(scope, receive, sender)
  File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 73, in app
    response = await f(request)
  File "/usr/local/lib/python3.10/site-packages/fastapi/routing.py", line 301, in app
    raw_response = await run_endpoint_function(
  File "/usr/local/lib/python3.10/site-packages/fastapi/routing.py", line 212, in run_endpoint_function
    return await dependant.call(**values)
  File "/usr/local/lib/python3.10/site-packages/ktransformers/server/api/openai/endpoints/chat.py", line 436, in chat_completion
    async for res in interface.inference(input_message, id, create.temperature, create.top_p, create.max_tokens, create.max_completion_tokens):
  File "/usr/local/lib/python3.10/site-packages/ktransformers/server/backend/interfaces/ktransformers.py", line 241, in inference
    async for v in super().inference(local_messages, thread_id, temperature, top_p, max_tokens, max_completion_tokens):
  File "/usr/local/lib/python3.10/site-packages/ktransformers/server/backend/interfaces/transformers.py", line 412, in inference
    for t in self.prefill(input_ids, self.check_is_new(thread_id), temperature, top_p, max_tokens, max_completion_tokens):
  File "/usr/local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 36, in generator_context
    response = gen.send(None)
  File "/usr/local/lib/python3.10/site-packages/ktransformers/server/backend/interfaces/ktransformers.py", line 229, in prefill
    self.prepare_logits_wrapper(input_ids, device, temperature, top_p)
  File "/usr/local/lib/python3.10/site-packages/ktransformers/server/backend/interfaces/transformers.py", line 231, in prepare_logits_wrapper
    self.model._get_logits_warper(generation_config)
  File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1729, in __getattr__
    raise AttributeError(f"'{type(self).__name__}' object has no attribute '{name}'")
AttributeError: 'DeepseekV3ForCausalLM' object has no attribute '_get_logits_warper'. Did you mean: '_get_logits_processor'?


K100非AI版都能适配那些大模型啊?
全部评论(14)
只看楼主
L
litzh
2楼
尝试回退transformers版本到4.43.2看能否解决,pip install transformers==4.43.2
2025/9/18
X
xingh
1楼
可以打印一下transformers和ktransformers的版本,看看是否兼容 import transformers, ktransformers print(transformers.__version__, ktransformers.__version__)
2025/9/18
网
网友yfri9U
回复 @xingh
import transformers, ktransformers transformers.__version__ '4.51.3' ktransformers.__version__ '0.3'
2025/9/18
X
xingh
回复 @网友yfri9U
从 HuggingFace transformers>=4.49 开始,_get_logits_warper 被移除了,统一用 _get_logits_processor 来处理 temperature / top_p / penalty 这些采样策略,但是 ktransformers==0.3 还在调用旧接口 _get_logits_warper,所以报错
2025/9/18
网
网友yfri9U
回复 @xingh
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. ktransformers 0.3+das.dtk2504 requires transformers==4.51.3, but you have transformers 4.48.2 which is incompatible. 但是 ktransformers 0.3+das.dtk2504 需要 transformers==4.51.3,没法降低 transformers 版本,怎么解决呢?
2025/9/18
全部12条回复
没有更多内容了
--
楼主
Level.1
0 帖子
楼主热帖
暂无数据