[Bug] lmdeploy chat model_name 对话的时候，报Aborted (core dumped)

jujunchen commented 3 weeks ago

Checklist

[ ] 1. I have searched related issues but cannot get the expected help.
[ ] 2. The bug has not been fixed in the latest version.

Describe the bug

lmdeploy chat /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b 运行在studio 开发机上的10% A100，跑起来后，对话就发生Aborted (core dumped) 退出

Reproduction

lmdeploy chat /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b

Environment

(lagent) root@intern-studio-045529:~/agent# lmdeploy check_env
sys.platform: linux
Python: 3.10.13 (main, Sep 11 2023, 13:44:35) [GCC 11.2.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0: NVIDIA A100-SXM4-80GB
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 12.2, V12.2.140
GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
PyTorch: 2.0.1
PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201703
  - Intel(R) oneAPI Math Kernel Library Version 2023.1-Product Build 20230303 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.7.3 (Git Hash 6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.7
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
  - CuDNN 8.5
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.0.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 

TorchVision: 0.15.2
LMDeploy: 0.4.2+
transformers: 4.38.2
gradio: 4.32.2
fastapi: 0.111.0
pydantic: 2.7.3
triton: 2.2.0

Error traceback

(lagent) root@intern-studio-045529:~/agent# lmdeploy chat /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b 
2024-06-04 16:31:27,178 - lmdeploy - WARNING - model_source: hf_model
2024-06-04 16:31:27,178 - lmdeploy - WARNING - kwargs max_batch_size is deprecated to initialize model, use TurbomindEngineConfig instead.
2024-06-04 16:31:27,178 - lmdeploy - WARNING - kwargs cache_max_entry_count is deprecated to initialize model, use TurbomindEngineConfig instead.
2024-06-04 16:31:29,669 - lmdeploy - WARNING - model_config:

[llama]
model_name = internlm2
tensor_para_size = 1
head_num = 16
kv_head_num = 8
vocab_size = 92544
num_layer = 24
inter_size = 8192
norm_eps = 1e-05
attn_bias = 0
start_id = 1
end_id = 2
session_len = 32776
weight_type = bf16
rotary_embedding = 128
rope_theta = 1000000.0
size_per_head = 128
group_size = 0
max_batch_size = 128
max_context_token_num = 1
step_length = 1
cache_max_entry_count = 0.8
cache_block_seq_len = 64
cache_chunk_size = -1
enable_prefix_caching = False
num_tokens_per_iter = 0
max_prefill_iters = 1
extra_tokens_per_iter = 0
use_context_fmha = 1
quant_policy = 0
max_position_embeddings = 32768
rope_scaling_factor = 0.0
use_dynamic_ntk = 0
use_logn_attn = 0
lora_policy = 
lora_r = 0
lora_scale = 0.0
lora_max_wo_r = 0
lora_rank_pattern = 
lora_scale_pattern = 

2024-06-04 16:31:30,671 - lmdeploy - WARNING - get 171 model params
2024-06-04 16:31:36,388 - lmdeploy - WARNING - Input chat template with model_name is None. Forcing to use internlm2                              
[WARNING] gemm_config.in is not found; using default GEMM algo
session 1

double enter to end input >>> 你好

<|im_start|>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.
<|im_end|>
<|im_start|>user
你好<|im_end|>
<|im_start|>assistant
 2024-06-04 16:31:40,244 - lmdeploy - WARNING - kwargs ignore_eos is deprecated for inference, use GenerationConfig instead.
2024-06-04 16:31:40,244 - lmdeploy - WARNING - kwargs random_seed is deprecated for inference, use GenerationConfig instead.
Aborted (core dumped)

irexyc commented 3 weeks ago

可能是显存的原因，可以试下

lmdeploy chat /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b --cache-max-entry-count 0.2

jujunchen commented 3 weeks ago

可能是显存的原因，可以试下

lmdeploy chat /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b --cache-max-entry-count 0.2

还是一样的情况，0.1也试了

lvhan028 commented 3 weeks ago

在 A100 单机上没有复现。需要在 intern-studio 下验证 @jujunchen 方便把 lmdeploy/turbomind/chat.py 中的 os.environ['TM_LOG_LEVEL'] = 'ERROR' 改成 os.environ['TM_LOG_LEVEL'] = 'INFO'，然后把执行日志贴上来么？

jujunchen commented 3 weeks ago

在 A100 单机上没有复现。需要在 intern-studio 下验证 @jujunchen 方便把 lmdeploy/turbomind/chat.py 中的 os.environ['TM_LOG_LEVEL'] = 'ERROR' 改成 os.environ['TM_LOG_LEVEL'] = 'INFO'，然后把执行日志贴上来么？

我是pip 安装的，没有源码

jujunchen commented 3 weeks ago

在 A100 单机上没有复现。需要在 intern-studio 下验证 @jujunchen 方便把 lmdeploy/turbomind/chat.py 中的 os.environ['TM_LOG_LEVEL'] = 'ERROR' 改成 os.environ['TM_LOG_LEVEL'] = 'INFO'，然后把执行日志贴上来么？

我从源码安装，发现可以对话了

InternLM / lmdeploy