search

microsoft / DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
https://www.deepspeed.ai/
Apache License 2.0
34.51k stars 4.03k forks source link

[BUG] Deepspeed MultiGpu inference not working with `Llama-2-13b-hf` #4874

Open Rishabhg71 opened 8 months ago

Rishabhg71 commented 8 months ago

Describe the bug

I was trying to run an inference with DeepSpeed on the Llama model, but when I ran deepspeed --num_gpus 4 script.py, the process terminated automatically after loading the checkpoint shards, without providing any additional information. Also, when running nvidia-smi, it appears that the model wasn’t even loaded, and no process was created, or it was created for a minimal amount of time.

[2023-12-26 13:12:37,547] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2023-12-26 13:12:40,313] [WARNING] [runner.py:202:fetch_hostfile] Unable to find hostfile, will proceed with training with local resources only.
[2023-12-26 13:12:40,352] [INFO] [runner.py:571:main] cmd = /opt/conda/bin/python3.10 -u -m deepspeed.launcher.launch --world_info=eyJsb2NhbGhvc3QiOiBbMCwgMSwgMiwgM119 --master_addr=127.0.0.1 --master_port=29500 --enable_each_rank_log=None script.py
[2023-12-26 13:12:42,637] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2023-12-26 13:12:43,352] [INFO] [launch.py:145:main] WORLD INFO DICT: {'localhost': [0, 1, 2, 3]}
[2023-12-26 13:12:43,352] [INFO] [launch.py:151:main] nnodes=1, num_local_procs=4, node_rank=0
[2023-12-26 13:12:43,352] [INFO] [launch.py:162:main] global_rank_mapping=defaultdict(<class 'list'>, {'localhost': [0, 1, 2, 3]})
[2023-12-26 13:12:43,352] [INFO] [launch.py:163:main] dist_world_size=4
[2023-12-26 13:12:43,352] [INFO] [launch.py:165:main] Setting CUDA_VISIBLE_DEVICES=0,1,2,3
[2023-12-26 13:12:46,236] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2023-12-26 13:12:46,236] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2023-12-26 13:12:46,253] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2023-12-26 13:12:46,254] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Loading checkpoint shards:  67%|█████████████████████████████████████▎                  | 2/3 [02:31<01:15, 75.65s/it][2023-12-26 13:15:58,389] [INFO] [launch.py:315:sigkill_handler] Killing subprocess 45345
[2023-12-26 13:15:58,511] [INFO] [launch.py:315:sigkill_handler] Killing subprocess 45346
[2023-12-26 13:16:00,882] [INFO] [launch.py:315:sigkill_handler] Killing subprocess 45347
[2023-12-26 13:16:03,251] [INFO] [launch.py:315:sigkill_handler] Killing subprocess 45348
[2023-12-26 13:16:05,660] [ERROR] [launch.py:321:sigkill_handler] ['/opt/conda/bin/python3.10', '-u', 'script.py', '--local_rank=3'] exits with return code = -9
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.104.12             Driver Version: 535.104.12   CUDA Version: 12.2     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  Tesla T4                       On  | 00000000:00:1B.0 Off |                    0 |
| N/A   22C    P8               9W /  70W |      2MiB / 15360MiB |      0%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+
|   1  Tesla T4                       On  | 00000000:00:1C.0 Off |                    0 |
| N/A   23C    P8               9W /  70W |      2MiB / 15360MiB |      0%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+
|   2  Tesla T4                       On  | 00000000:00:1D.0 Off |                    0 |
| N/A   23C    P8               9W /  70W |      2MiB / 15360MiB |      0%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+
|   3  Tesla T4                       On  | 00000000:00:1E.0 Off |                    0 |
| N/A   22C    P8               8W /  70W |      2MiB / 15360MiB |      0%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
|  No running processes found                                                           |
+---------------------------------------------------------------------------------------+

To Reproduce

from transformers import LlamaForCausalLM, AutoTokenizer, AutoModel

import deepspeed import torch

Specify the model name

model_name = "meta-llama/Llama-2-13b-hf"

Load the tokenizer

tokenizer = AutoTokenizer.from_pretrained(model_name)

Load the model

model = LlamaForCausalLM.from_pretrained(modelname, token="hf")

model = AutoModel.from_pretrained(modelname, token="hf")

Initialize the DeepSpeed-Inference engine

ds_engine = deepspeed.init_inference(model, mp_size=2, dtype=torch.half) model = ds_engine.module output = model('Input String')

This original script is taken from https://www.deepspeed.ai/tutorials/inference-tutorial/#initializing-for-inference 

**Expected behavior**
A successful inference output 

**ds_report output**
```bash
[2023-12-26 15:09:06,338] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
--------------------------------------------------
DeepSpeed C++/CUDA extension op report
--------------------------------------------------
NOTE: Ops not installed will be just-in-time (JIT) compiled at
      runtime if needed. Op compatibility means that your system
      meet the required dependencies to JIT install the op.
--------------------------------------------------
JIT compiled ops requires ninja
ninja .................. [OKAY]
--------------------------------------------------
op name ................ installed .. compatible
--------------------------------------------------
 [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
 [WARNING]  async_io: please install the libaio-dev package with apt
 [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
async_io ............... [NO] ....... [NO]
fused_adam ............. [NO] ....... [OKAY]
cpu_adam ............... [NO] ....... [OKAY]
cpu_adagrad ............ [NO] ....... [OKAY]
cpu_lion ............... [NO] ....... [OKAY]
 [WARNING]  Please specify the CUTLASS repo directory as environment variable $CUTLASS_PATH
evoformer_attn ......... [NO] ....... [NO]
fused_lamb ............. [NO] ....... [OKAY]
fused_lion ............. [NO] ....... [OKAY]
inference_core_ops ..... [NO] ....... [OKAY]
cutlass_ops ............ [NO] ....... [OKAY]
quantizer .............. [NO] ....... [OKAY]
ragged_device_ops ...... [NO] ....... [OKAY]
ragged_ops ............. [NO] ....... [OKAY]
random_ltd ............. [NO] ....... [OKAY]
 [WARNING]  sparse_attn requires a torch version >= 1.5 and < 2.0 but detected 2.1
 [WARNING]  using untested triton version (2.1.0), only 1.0.0 is known to be compatible
sparse_attn ............ [NO] ....... [NO]
spatial_inference ...... [NO] ....... [OKAY]
transformer ............ [NO] ....... [OKAY]
stochastic_transformer . [NO] ....... [OKAY]
transformer_inference .. [NO] ....... [OKAY]
--------------------------------------------------
DeepSpeed general environment info:
torch install path ............... ['/opt/conda/lib/python3.10/site-packages/torch']
torch version .................... 2.1.2+cu121
deepspeed install path ........... ['/opt/conda/lib/python3.10/site-packages/deepspeed']
deepspeed info ................... 0.12.6, unknown, unknown
torch cuda version ............... 12.1
torch hip version ................ None
nvcc version ..................... 12.1
deepspeed wheel compiled w. ...... torch 0.0, cuda 0.0
shared memory (/dev/shm) size .... 93.30 GB

System info (please complete the following information):

mrwyattii commented 7 months ago

Hi @Rishabhg71 I suspect that running with mp_size=2, in the script and --num_gpus 4 is causing a problem. Please make sure these values match.

Additionally, for Llama-2 models we suggest using the latest DeepSpeed-MII to run inference.

YuWang916 commented 6 months ago

Hello @mrwyattii ! I am facing the same error [2024-02-12 22:12:33,072] [ERROR] [launch.py:321:sigkill_handler] ... exits with return code = -9. For reference, I have followed the DS Inference HF example , and successfully ran inference using the Falco-40B model with 8 A100 GPUs. Then I switched from Falcon-40B to Falcon-180B, and this error above occurred. From the metrics graph, the GPUs are not even started. It happens right after the model was successfully loaded with message Loading checkpoint shards: 100%. Could you provided any insights into this issue? Thank you!