无法使用lmdeploy chat

Comienza reproduciendo el comando indicado lmdeploy chat turbomind con la ruta del modelo mostrada y el valor de --model-name. Investiga el fallo CUDA_ERROR_INVALID_CONTEXT después del primer prompt, junto con las advertencias sobre la ausencia de tokenizer.json y la configuración de GEMM. Se considera terminado cuando se identifica una corrección confirmada del entorno o de la invocación que permite al comando de chat generar una respuesta sin abortarse.

我按照教程配置了所有的环境内容，但是一运行就报错..
后面我离线转换的也是报错这个

(lmdeploy) root@intern-studio:~# lmdeploy chat turbomind /share/temp/model_repos/internlm-chat-7b/ --model-name internlm-chat-7b
model_source: hf_model
WARNING: Can not find tokenizer.json. It may take long time to initialize the tokenizer.
WARNING: Can not find tokenizer.json. It may take long time to initialize the tokenizer.
model_config:
{
"model_name": "internlm-chat-7b",
"tensor_para_size": 1,
"head_num": 32,
"kv_head_num": 32,
"vocab_size": 103168,
"num_layer": 32,
"inter_size": 11008,
"norm_eps": 1e-06,
"attn_bias": 1,
"start_id": 1,
"end_id": 2,
"session_len": 2056,
"weight_type": "fp16",
"rotary_embedding": 128,
"rope_theta": 10000.0,
"size_per_head": 128,
"group_size": 0,
"max_batch_size": 64,
"max_context_token_num": 1,
"step_length": 1,
"cache_max_entry_count": 0.5,
"cache_block_seq_len": 128,
"cache_chunk_size": 1,
"use_context_fmha": 1,
"quant_policy": 0,
"max_position_embeddings": 2048,
"rope_scaling_factor": 0.0,
"use_logn_attn": 0
}
get 323 model params
[WARNING] gemm_config.in is not found; using default GEMM algo
session 1

double enter to end input >>> hello

<|System|>:You are an AI assistant whose name is InternLM (书生·浦语).

• InternLM (书生·浦语) is a conversational language model that is developed by Shanghai AI Laboratory (上海人工智能实验室). It is designed to be helpful, honest, and harmless.
• InternLM (书生·浦语) can understand and communicate fluently in the language chosen by the user such as English and 中文.

<|User|>:hello
<|Bot|>: [AMP ERROR][CudaFrontend.cpp:94][1705496068:532304]failed to call cuCtxGetDevice(&device), error code: CUDA_ERROR_INVALID_CONTEXT

===============================================

Back trace dump:
/usr/local/harp/lib/libvirtdev-frontend.so.0(LogStream::PrintBacktrace()+0x52) [0x7fc0d92cc302]
/lib/x86_64-linux-gnu/libcuda.so.1(CudaFeApiStateData::GetCurrentDevicePciBusId(Frontend*, int const*)+0x241) [0x7fc0d94fb471]
/lib/x86_64-linux-gnu/libcuda.so.1(python: CudaFrontend.cpp:94: static const string& CudaFeApiStateData::GetCurrentDevicePciBusId(Frontend*, const CUdevice*): Assertion `0' failed.
Aborted (core dumped)