尝试回退transformers版本到4.43.2看能否解决,pip install transformers==4.43.2
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'?
暂无数据