[Bug] lmdeploy - ERROR - run out of tokens. session_id=1

cuong-dyania commented 2 months ago

Checklist

[X] 1. I have searched related issues but cannot get the expected help.
[X] 2. The bug has not been fixed in the latest version.
[X] 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.

Describe the bug

The bug arose when I ran lmdeploy with Llama 3 70B during inference. I tried to generate text completion for a very long note (around 8K tokens).

I tried to include gen_config such as gen_config = GenerationConfig(min_new_tokens = 100) but none of them worked.

Reproduction

from transformers import AutoTokenizer, AutoModelForCausalLM from lmdeploy import pipeline, GenerationConfig, TurbomindEngineConfig

model_id = "meta-llama/Meta-Llama-3-70B"

backend_config = TurbomindEngineConfig(cache_max_entry_count=0.2, tp =4) pipe = pipeline(model_id, backend_config=backend_config)

prompts = [' A very long prompt........']

response = pipe(prompts)

I tried to include generation config but the same error still showed up. gen_config = GenerationConfig(min_new_tokens = 100)
response = pipe(prompts, gen_config = gen_config)

Environment

NA

Error traceback

No response

lvhan028 commented 2 months ago

Please kindly paste the information after running lmdeploy check_env

cuong-dyania commented 2 months ago

Thanks for your quick reply, lvhan028. The below is the information that you need:

sys.platform: linux Python: 3.12.4 | packaged by conda-forge | (main, Jun 17 2024, 10:23:07) [GCC 12.3.0] CUDA available: True MUSA available: False numpy_random_seed: 2147483648 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /usr NVCC: Cuda compilation tools, release 12.2, V12.2.140 GCC: gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 PyTorch: 2.3.1+cu121 PyTorch compiling details: PyTorch built with:

GCC 9.3
C++ Version: 201703
Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications
Intel(R) MKL-DNN v3.3.6 (Git Hash 86e6af5974177e513fd3fee58425e1063e7f1361)
OpenMP 201511 (a.k.a. OpenMP 4.5)
LAPACK is enabled (usually provided by MKL)
NNPACK is enabled
CPU capability usage: AVX2
CUDA Runtime 12.1
NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-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_90,code=sm_90
CuDNN 8.9.2
Magma 2.6.1
Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=12.1, CUDNN_VERSION=8.9.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -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 -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=2.3.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF,

TorchVision: 0.18.1+cu121 LMDeploy: 0.5.3+ transformers: 4.41.2 gradio: Not Found fastapi: 0.112.0 pydantic: 2.8.2 triton: 2.3.1 NVIDIA Topology: GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 CPU Affinity NUMA Affinity GPU NUMA ID GPU0 X NV12 NV12 NV12 NV12 NV12 NV12 NV12 0-63,128-191 0 N/A GPU1 NV12 X NV12 NV12 NV12 NV12 NV12 NV12 0-63,128-191 0 N/A GPU2 NV12 NV12 X NV12 NV12 NV12 NV12 NV12 0-63,128-191 0 N/A GPU3 NV12 NV12 NV12 X NV12 NV12 NV12 NV12 0-63,128-191 0 N/A GPU4 NV12 NV12 NV12 NV12 X NV12 NV12 NV12 64-127,192-255 1 N/A GPU5 NV12 NV12 NV12 NV12 NV12 X NV12 NV12 64-127,192-255 1 N/A GPU6 NV12 NV12 NV12 NV12 NV12 NV12 X NV12 64-127,192-255 1 N/A GPU7 NV12 NV12 NV12 NV12 NV12 NV12 NV12 X 64-127,192-255 1 N/A

Legend:

X = Self SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI) NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU) PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge) PIX = Connection traversing at most a single PCIe bridge NV# = Connection traversing a bonded set of # NVLinks

lvhan028 commented 2 months ago

I suggest using the default cache_max_entry_count. If OOM happens, decrease its value. Regarding the explanation about cache_max_entry_count, please refer to the note in https://lmdeploy.readthedocs.io/en/latest/get_started.html

InternLM / lmdeploy