是否支持单显卡MIG

[nic648]

有一块A100，80G的显卡
当前已经MIG了

Fri Dec 20 18:39:26 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.127.08 Driver Version: 550.127.08 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| 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 NVIDIA A100 80GB PCIe Off | 00000000:08:00.0 Off | On |
| N/A 56C P0 68W / 300W | 63MiB / 81920MiB | N/A Default |
| | | Enabled |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| MIG devices: |
+------------------+----------------------------------+-----------+-----------------------+
| GPU GI CI MIG | Memory-Usage | Vol| Shared |
| ID ID Dev | BAR1-Usage | SM Unc| CE ENC DEC OFA JPG |
| | | ECC| |
|==================+==================================+===========+=======================|
| 0 2 0 0 | 38MiB / 40192MiB | 14 0 | 3 0 2 0 0 |
| | 0MiB / 65535MiB | | |
+------------------+ +-----------+-----------------------+
| 0 2 1 1 | | 14 0 | 3 0 2 0 0 |
| | | | |
+------------------+ +-----------+-----------------------+
| 0 2 2 2 | | 14 0 | 3 0 2 0 0 |
| | | | |
+------------------+----------------------------------+-----------+-----------------------+
| 0 3 0 3 | 13MiB / 19968MiB | 14 0 | 1 0 1 0 0 |
| | 0MiB / 32767MiB | | |
+------------------+----------------------------------+-----------+-----------------------+
| 0 4 0 4 | 13MiB / 19968MiB | 14 0 | 1 0 1 0 0 |
| | 0MiB / 32767MiB | | |
+------------------+----------------------------------+-----------+-----------------------+

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

问题一：
#写成mig-id，"cuda:2" 显示未找到
magic-pdf.config配置文件是否支持MIG
{
"bucket_info": {
"bucket-name-1": [
"ak",
"sk",
"endpoint"
],
"bucket-name-2": [
"ak",
"sk",
"endpoint"
]
},
"models-dir": "/root/.cache/modelscope/hub/opendatalab/PDF-Extract-Kit-1___0/models",
"layoutreader-model-dir": "/root/.cache/modelscope/hub/ppaanngggg/layoutreader",
"device-mode": "cuda", #写成"cuda:2" 显示未找到
"layout-config": {
"model": "layoutlmv3"
},
"formula-config": {
"mfd_model": "yolo_v8_mfd",
"mfr_model": "unimernet_small",
"enable": true
},
"table-config": {
"model": "rapid_table",
"enable": true,
"max_time": 400
},
"config_version": "1.0.0"
}

问题二：
多GPU模式
server = ls.LitServer(MinerUAPI(), accelerator='gpu', devices=[0,1,2,3,4], timeout=False)
server.run(port=8080)
Model initialization complete!
Process SpawnProcess-2:
Traceback (most recent call last):
File "/root/anaconda3/envs/MinerU/lib/python3.10/multiprocessing/managers.py", line 810, in _callmethod
conn = self._tls.connection
AttributeError: 'ForkAwareLocal' object has no attribute 'connection'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/root/anaconda3/envs/MinerU/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
self.run()
File "/root/anaconda3/envs/MinerU/lib/python3.10/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/root/anaconda3/envs/MinerU/lib/python3.10/site-packages/litserve/loops.py", line 417, in inference_worker
if workers_setup_status:
File "", line 2, in len
File "/root/anaconda3/envs/MinerU/lib/python3.10/multiprocessing/managers.py", line 814, in _callmethod
self._connect()
File "/root/anaconda3/envs/MinerU/lib/python3.10/multiprocessing/managers.py", line 801, in _connect
conn = self._Client(self._token.address, authkey=self._authkey)
File "/root/anaconda3/envs/MinerU/lib/python3.10/multiprocessing/connection.py", line 502, in Client
c = SocketClient(address)
File "/root/anaconda3/envs/MinerU/lib/python3.10/multiprocessing/connection.py", line 630, in SocketClient
s.connect(address)
FileNotFoundError: [Errno 2] No such file or directory