github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-08-30 17:25:30 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

When responding to dialogues, CPU and memory usage surge to around 70%, while GPU usage remains below 10%. #1576

New Issue
Closed
opened 2025-11-11 14:47:41 -06:00 by GiteaMirror · 0 comments
GiteaMirror commented 2025-11-11 14:47:41 -06:00
Owner
Copy Link
Copy Source

Originally created by @ddxl123 on GitHub (Jul 21, 2024).

When responding to dialogues, CPU and memory usage surge to around 70%, while GPU usage remains below 10%.
Docker Desktop 4.32.0

ollama v0.2.7
Model: llama3:70b
Open-webui v0.3.10
cuda v12.5

-PC-
cpu: intel i9-14900k
4080super，NVIDIA graphics card driver version:32.0.15.5599
RAM: 64G

Windows 11 x64
Browser is edge v126.0.2592.113.

Docker Desktop Containers log:

2024-07-22 06:00:54 Loading WEBUI_SECRET_KEY from file, not provided as an environment variable.
2024-07-22 06:00:54 Generating WEBUI_SECRET_KEY
2024-07-22 06:00:54 Loading WEBUI_SECRET_KEY from .webui_secret_key
2024-07-22 06:00:54 CUDA is enabled, appending LD_LIBRARY_PATH to include torch/cudnn & cublas libraries.
2024-07-22 06:01:09 /app
2024-07-22 06:01:09 
2024-07-22 06:01:09   ___                    __        __   _     _   _ ___ 
2024-07-22 06:01:09  / _ \ _ __   ___ _ __   \ \      / /__| |__ | | | |_ _|
2024-07-22 06:01:09 | | | | '_ \ / _ \ '_ \   \ \ /\ / / _ \ '_ \| | | || | 
2024-07-22 06:01:09 | |_| | |_) |  __/ | | |   \ V  V /  __/ |_) | |_| || | 
2024-07-22 06:01:09  \___/| .__/ \___|_| |_|    \_/\_/ \___|_.__/ \___/|___|
2024-07-22 06:01:09       |_|                                               
2024-07-22 06:01:09 
2024-07-22 06:01:09       
2024-07-22 06:01:09 v0.3.10 - building the best open-source AI user interface.
2024-07-22 06:01:09 
2024-07-22 06:01:09 https://github.com/open-webui/open-webui
2024-07-22 06:01:01 USER_AGENT environment variable not set, consider setting it to identify your requests.
2024-07-22 06:01:08 INFO:     Started server process [1]
2024-07-22 06:01:08 INFO:     Waiting for application startup.
2024-07-22 06:01:09 INFO  [alembic.runtime.migration] Context impl SQLiteImpl.
2024-07-22 06:01:09 INFO  [alembic.runtime.migration] Will assume non-transactional DDL.
2024-07-22 06:01:09 INFO:     Application startup complete.
2024-07-22 06:01:09 INFO:     Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)
2024-07-22 06:01:09 
2024-07-22 06:01:24 INFO  [apps.openai.main] get_all_models()
2024-07-22 06:01:24 INFO  [apps.ollama.main] get_all_models()
2024-07-22 06:01:24 INFO:     172.17.0.1:52334 - "GET /static/splash.png HTTP/1.1" 200 OK
2024-07-22 06:01:24 INFO:     127.0.0.1:52592 - "GET /health HTTP/1.1" 200 OK
2024-07-22 06:01:24 INFO:     172.17.0.1:52334 - "GET /manifest.json HTTP/1.1" 200 OK
2024-07-22 06:01:24 INFO:     172.17.0.1:52334 - "GET /api/config HTTP/1.1" 200 OK
2024-07-22 06:01:24 INFO:     172.17.0.1:52334 - "GET /ws/socket.io/?EIO=4&transport=polling&t=P3NK5Qx HTTP/1.1" 200 OK
2024-07-22 06:01:24 INFO:     172.17.0.1:52344 - "GET /api/v1/auths/ HTTP/1.1" 401 Unauthorized
2024-07-22 06:01:25 INFO:     ('172.17.0.1', 40278) - "WebSocket /ws/socket.io/?EIO=4&transport=websocket&sid=C5u-BpFM8ibdiddbAAAA" [accepted]
2024-07-22 06:01:25 INFO:     connection open
2024-07-22 06:01:25 INFO:     172.17.0.1:52344 - "POST /ws/socket.io/?EIO=4&transport=polling&t=P3NK5Rt&sid=C5u-BpFM8ibdiddbAAAA HTTP/1.1" 200 OK
2024-07-22 06:01:25 INFO:     172.17.0.1:52334 - "GET /ws/socket.io/?EIO=4&transport=polling&t=P3NK5Ru&sid=C5u-BpFM8ibdiddbAAAA HTTP/1.1" 200 OK
2024-07-22 06:01:25 INFO:     172.17.0.1:52334 - "GET /static/favicon.png HTTP/1.1" 200 OK
2024-07-22 06:01:26 INFO  [apps.webui.models.auths] authenticate_user: 1033839760@qq.com
2024-07-22 06:01:26 INFO:     172.17.0.1:52334 - "POST /api/v1/auths/signin HTTP/1.1" 200 OK
2024-07-22 06:01:26 user-join AlgSpev31drlO-w3AAAB {'auth': {'token': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6Ijc4MmI3ZWM5LWM2NmEtNDNlYy1hNmQ4LTg2YmI2M2Y1MjYyOSJ9.QRUbWeJDLAwZQdinCT32LWSqgWnWSEImWOvsFZHdWtY'}}
2024-07-22 06:01:26 user long(782b7ec9-c66a-43ec-a6d8-86bb63f52629) connected with session ID AlgSpev31drlO-w3AAAB
2024-07-22 06:01:26 INFO:     172.17.0.1:52334 - "GET /api/changelog HTTP/1.1" 200 OK
2024-07-22 06:01:26 INFO:     172.17.0.1:52344 - "GET /api/v1/users/user/settings HTTP/1.1" 200 OK
2024-07-22 06:01:26 INFO  [apps.openai.main] get_all_models()
2024-07-22 06:01:26 INFO  [apps.ollama.main] get_all_models()
2024-07-22 06:01:26 INFO:     172.17.0.1:52334 - "GET /api/v1/prompts/ HTTP/1.1" 200 OK
2024-07-22 06:01:26 INFO:     172.17.0.1:52344 - "GET /api/models HTTP/1.1" 200 OK
2024-07-22 06:01:26 INFO:     172.17.0.1:40284 - "GET /api/v1/documents/ HTTP/1.1" 200 OK
2024-07-22 06:01:26 INFO:     172.17.0.1:40302 - "GET /api/v1/configs/banners HTTP/1.1" 200 OK
2024-07-22 06:01:26 INFO:     172.17.0.1:40292 - "GET /api/v1/functions/ HTTP/1.1" 200 OK
2024-07-22 06:01:26 INFO:     172.17.0.1:40288 - "GET /api/v1/tools/ HTTP/1.1" 200 OK
2024-07-22 06:01:26 INFO:     172.17.0.1:52334 - "GET /api/v1/chats/tags/all HTTP/1.1" 200 OK
2024-07-22 06:01:26 INFO:     172.17.0.1:52334 - "POST /api/v1/chats/tags HTTP/1.1" 200 OK
2024-07-22 06:01:26 INFO:     172.17.0.1:40288 - "GET /ollama/api/version HTTP/1.1" 200 OK
2024-07-22 06:01:26 INFO:     172.17.0.1:40292 - "GET /api/v1/users/user/settings HTTP/1.1" 200 OK
2024-07-22 06:01:26 INFO:     172.17.0.1:40292 - "GET /api/v1/chats/ HTTP/1.1" 200 OK
2024-07-22 06:01:35 INFO:     172.17.0.1:54990 - "POST /api/v1/chats/new HTTP/1.1" 200 OK
2024-07-22 06:01:35 INFO:     172.17.0.1:54990 - "GET /api/v1/chats/ HTTP/1.1" 200 OK
2024-07-22 06:01:35 INFO  [apps.ollama.main] url: http://host.docker.internal:11434
2024-07-22 06:01:54 INFO:     127.0.0.1:60406 - "GET /health HTTP/1.1" 200 OK
2024-07-22 06:02:15 INFO:     172.17.0.1:54990 - "POST /ollama/api/chat HTTP/1.1" 200 OK
2024-07-22 06:02:24 INFO:     127.0.0.1:37392 - "GET /health HTTP/1.1" 200 OK
2024-07-22 06:02:47 INFO:     172.17.0.1:54990 - "POST /api/chat/completed HTTP/1.1" 200 OK
2024-07-22 06:02:47 INFO:     172.17.0.1:54990 - "POST /api/v1/chats/4601439b-225d-4c58-abf2-4570ed59a740 HTTP/1.1" 200 OK
2024-07-22 06:02:47 INFO:     172.17.0.1:54990 - "GET /api/v1/chats/ HTTP/1.1" 200 OK
2024-07-22 06:02:47 INFO:     172.17.0.1:54990 - "POST /api/v1/chats/4601439b-225d-4c58-abf2-4570ed59a740 HTTP/1.1" 200 OK
2024-07-22 06:02:47 INFO:     172.17.0.1:54990 - "GET /api/v1/chats/ HTTP/1.1" 200 OK
2024-07-22 06:02:47 INFO  [apps.ollama.main] url: http://host.docker.internal:11434
2024-07-22 06:02:53 generate_title
2024-07-22 06:02:53 llama3:70b
2024-07-22 06:02:53 generate_ollama_chat_completion
2024-07-22 06:02:53 INFO:     172.17.0.1:54990 - "POST /api/task/title/completions HTTP/1.1" 200 OK
2024-07-22 06:02:53 INFO:     172.17.0.1:54990 - "POST /api/v1/chats/4601439b-225d-4c58-abf2-4570ed59a740 HTTP/1.1" 200 OK
2024-07-22 06:02:53 INFO:     172.17.0.1:54990 - "GET /api/v1/chats/ HTTP/1.1" 200 OK
2024-07-22 06:02:53 INFO:     172.17.0.1:54990 - "GET /api/v1/chats/ HTTP/1.1" 200 OK
2024-07-22 06:02:54 INFO:     127.0.0.1:53210 - "GET /health HTTP/1.1" 200 OK
2024-07-22 06:03:24 ['AlgSpev31drlO-w3AAAB']
2024-07-22 06:03:24 INFO:     127.0.0.1:37912 - "GET /health HTTP/1.1" 200 OK
2024-07-22 06:03:54 INFO:     127.0.0.1:46856 - "GET /health HTTP/1.1" 200 OK
2024-07-22 06:04:24 INFO:     127.0.0.1:41006 - "GET /health HTTP/1.1" 200 OK
2024-07-22 06:04:54 INFO:     127.0.0.1:50412 - "GET /health HTTP/1.1" 200 OK

Running nvidia-smi in Docker Desktop Containers:

+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 555.52.01              Driver Version: 555.99         CUDA Version: 12.5     |
|-----------------------------------------+------------------------+----------------------+
| 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 GeForce RTX 4080 ...    On  |   00000000:01:00.0  On |                  N/A |
| 35%   34C    P8             21W /  320W |    2025MiB /  16376MiB |      2%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+
                                                                                         
+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|    0   N/A  N/A         1      C   /python3.11                                 N/A      |
+-----------------------------------------------------------------------------------------+
#
Originally created by @ddxl123 on GitHub (Jul 21, 2024). When responding to dialogues, CPU and memory usage surge to around 70%, while GPU usage remains below 10%. Docker Desktop 4.32.0 ollama v0.2.7 Model: llama3:70b Open-webui v0.3.10 cuda v12.5 -PC- cpu: intel i9-14900k 4080super，NVIDIA graphics card driver version:32.0.15.5599 RAM: 64G Windows 11 x64 Browser is edge v126.0.2592.113. Docker Desktop Containers log: ``` 2024-07-22 06:00:54 Loading WEBUI_SECRET_KEY from file, not provided as an environment variable. 2024-07-22 06:00:54 Generating WEBUI_SECRET_KEY 2024-07-22 06:00:54 Loading WEBUI_SECRET_KEY from .webui_secret_key 2024-07-22 06:00:54 CUDA is enabled, appending LD_LIBRARY_PATH to include torch/cudnn & cublas libraries. 2024-07-22 06:01:09 /app 2024-07-22 06:01:09 2024-07-22 06:01:09 ___ __ __ _ _ _ ___ 2024-07-22 06:01:09 / _ \ _ __ ___ _ __ \ \ / /__| |__ | | | |_ _| 2024-07-22 06:01:09 | | | | '_ \ / _ \ '_ \ \ \ /\ / / _ \ '_ \| | | || | 2024-07-22 06:01:09 | |_| | |_) | __/ | | | \ V V / __/ |_) | |_| || | 2024-07-22 06:01:09 \___/| .__/ \___|_| |_| \_/\_/ \___|_.__/ \___/|___| 2024-07-22 06:01:09 |_| 2024-07-22 06:01:09 2024-07-22 06:01:09 2024-07-22 06:01:09 v0.3.10 - building the best open-source AI user interface. 2024-07-22 06:01:09 2024-07-22 06:01:09 https://github.com/open-webui/open-webui 2024-07-22 06:01:01 USER_AGENT environment variable not set, consider setting it to identify your requests. 2024-07-22 06:01:08 INFO: Started server process [1] 2024-07-22 06:01:08 INFO: Waiting for application startup. 2024-07-22 06:01:09 INFO [alembic.runtime.migration] Context impl SQLiteImpl. 2024-07-22 06:01:09 INFO [alembic.runtime.migration] Will assume non-transactional DDL. 2024-07-22 06:01:09 INFO: Application startup complete. 2024-07-22 06:01:09 INFO: Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit) 2024-07-22 06:01:09 2024-07-22 06:01:24 INFO [apps.openai.main] get_all_models() 2024-07-22 06:01:24 INFO [apps.ollama.main] get_all_models() 2024-07-22 06:01:24 INFO: 172.17.0.1:52334 - "GET /static/splash.png HTTP/1.1" 200 OK 2024-07-22 06:01:24 INFO: 127.0.0.1:52592 - "GET /health HTTP/1.1" 200 OK 2024-07-22 06:01:24 INFO: 172.17.0.1:52334 - "GET /manifest.json HTTP/1.1" 200 OK 2024-07-22 06:01:24 INFO: 172.17.0.1:52334 - "GET /api/config HTTP/1.1" 200 OK 2024-07-22 06:01:24 INFO: 172.17.0.1:52334 - "GET /ws/socket.io/?EIO=4&transport=polling&t=P3NK5Qx HTTP/1.1" 200 OK 2024-07-22 06:01:24 INFO: 172.17.0.1:52344 - "GET /api/v1/auths/ HTTP/1.1" 401 Unauthorized 2024-07-22 06:01:25 INFO: ('172.17.0.1', 40278) - "WebSocket /ws/socket.io/?EIO=4&transport=websocket&sid=C5u-BpFM8ibdiddbAAAA" [accepted] 2024-07-22 06:01:25 INFO: connection open 2024-07-22 06:01:25 INFO: 172.17.0.1:52344 - "POST /ws/socket.io/?EIO=4&transport=polling&t=P3NK5Rt&sid=C5u-BpFM8ibdiddbAAAA HTTP/1.1" 200 OK 2024-07-22 06:01:25 INFO: 172.17.0.1:52334 - "GET /ws/socket.io/?EIO=4&transport=polling&t=P3NK5Ru&sid=C5u-BpFM8ibdiddbAAAA HTTP/1.1" 200 OK 2024-07-22 06:01:25 INFO: 172.17.0.1:52334 - "GET /static/favicon.png HTTP/1.1" 200 OK 2024-07-22 06:01:26 INFO [apps.webui.models.auths] authenticate_user: 1033839760@qq.com 2024-07-22 06:01:26 INFO: 172.17.0.1:52334 - "POST /api/v1/auths/signin HTTP/1.1" 200 OK 2024-07-22 06:01:26 user-join AlgSpev31drlO-w3AAAB {'auth': {'token': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6Ijc4MmI3ZWM5LWM2NmEtNDNlYy1hNmQ4LTg2YmI2M2Y1MjYyOSJ9.QRUbWeJDLAwZQdinCT32LWSqgWnWSEImWOvsFZHdWtY'}} 2024-07-22 06:01:26 user long(782b7ec9-c66a-43ec-a6d8-86bb63f52629) connected with session ID AlgSpev31drlO-w3AAAB 2024-07-22 06:01:26 INFO: 172.17.0.1:52334 - "GET /api/changelog HTTP/1.1" 200 OK 2024-07-22 06:01:26 INFO: 172.17.0.1:52344 - "GET /api/v1/users/user/settings HTTP/1.1" 200 OK 2024-07-22 06:01:26 INFO [apps.openai.main] get_all_models() 2024-07-22 06:01:26 INFO [apps.ollama.main] get_all_models() 2024-07-22 06:01:26 INFO: 172.17.0.1:52334 - "GET /api/v1/prompts/ HTTP/1.1" 200 OK 2024-07-22 06:01:26 INFO: 172.17.0.1:52344 - "GET /api/models HTTP/1.1" 200 OK 2024-07-22 06:01:26 INFO: 172.17.0.1:40284 - "GET /api/v1/documents/ HTTP/1.1" 200 OK 2024-07-22 06:01:26 INFO: 172.17.0.1:40302 - "GET /api/v1/configs/banners HTTP/1.1" 200 OK 2024-07-22 06:01:26 INFO: 172.17.0.1:40292 - "GET /api/v1/functions/ HTTP/1.1" 200 OK 2024-07-22 06:01:26 INFO: 172.17.0.1:40288 - "GET /api/v1/tools/ HTTP/1.1" 200 OK 2024-07-22 06:01:26 INFO: 172.17.0.1:52334 - "GET /api/v1/chats/tags/all HTTP/1.1" 200 OK 2024-07-22 06:01:26 INFO: 172.17.0.1:52334 - "POST /api/v1/chats/tags HTTP/1.1" 200 OK 2024-07-22 06:01:26 INFO: 172.17.0.1:40288 - "GET /ollama/api/version HTTP/1.1" 200 OK 2024-07-22 06:01:26 INFO: 172.17.0.1:40292 - "GET /api/v1/users/user/settings HTTP/1.1" 200 OK 2024-07-22 06:01:26 INFO: 172.17.0.1:40292 - "GET /api/v1/chats/ HTTP/1.1" 200 OK 2024-07-22 06:01:35 INFO: 172.17.0.1:54990 - "POST /api/v1/chats/new HTTP/1.1" 200 OK 2024-07-22 06:01:35 INFO: 172.17.0.1:54990 - "GET /api/v1/chats/ HTTP/1.1" 200 OK 2024-07-22 06:01:35 INFO [apps.ollama.main] url: http://host.docker.internal:11434 2024-07-22 06:01:54 INFO: 127.0.0.1:60406 - "GET /health HTTP/1.1" 200 OK 2024-07-22 06:02:15 INFO: 172.17.0.1:54990 - "POST /ollama/api/chat HTTP/1.1" 200 OK 2024-07-22 06:02:24 INFO: 127.0.0.1:37392 - "GET /health HTTP/1.1" 200 OK 2024-07-22 06:02:47 INFO: 172.17.0.1:54990 - "POST /api/chat/completed HTTP/1.1" 200 OK 2024-07-22 06:02:47 INFO: 172.17.0.1:54990 - "POST /api/v1/chats/4601439b-225d-4c58-abf2-4570ed59a740 HTTP/1.1" 200 OK 2024-07-22 06:02:47 INFO: 172.17.0.1:54990 - "GET /api/v1/chats/ HTTP/1.1" 200 OK 2024-07-22 06:02:47 INFO: 172.17.0.1:54990 - "POST /api/v1/chats/4601439b-225d-4c58-abf2-4570ed59a740 HTTP/1.1" 200 OK 2024-07-22 06:02:47 INFO: 172.17.0.1:54990 - "GET /api/v1/chats/ HTTP/1.1" 200 OK 2024-07-22 06:02:47 INFO [apps.ollama.main] url: http://host.docker.internal:11434 2024-07-22 06:02:53 generate_title 2024-07-22 06:02:53 llama3:70b 2024-07-22 06:02:53 generate_ollama_chat_completion 2024-07-22 06:02:53 INFO: 172.17.0.1:54990 - "POST /api/task/title/completions HTTP/1.1" 200 OK 2024-07-22 06:02:53 INFO: 172.17.0.1:54990 - "POST /api/v1/chats/4601439b-225d-4c58-abf2-4570ed59a740 HTTP/1.1" 200 OK 2024-07-22 06:02:53 INFO: 172.17.0.1:54990 - "GET /api/v1/chats/ HTTP/1.1" 200 OK 2024-07-22 06:02:53 INFO: 172.17.0.1:54990 - "GET /api/v1/chats/ HTTP/1.1" 200 OK 2024-07-22 06:02:54 INFO: 127.0.0.1:53210 - "GET /health HTTP/1.1" 200 OK 2024-07-22 06:03:24 ['AlgSpev31drlO-w3AAAB'] 2024-07-22 06:03:24 INFO: 127.0.0.1:37912 - "GET /health HTTP/1.1" 200 OK 2024-07-22 06:03:54 INFO: 127.0.0.1:46856 - "GET /health HTTP/1.1" 200 OK 2024-07-22 06:04:24 INFO: 127.0.0.1:41006 - "GET /health HTTP/1.1" 200 OK 2024-07-22 06:04:54 INFO: 127.0.0.1:50412 - "GET /health HTTP/1.1" 200 OK ``` Running `nvidia-smi` in Docker Desktop Containers: ``` +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 555.52.01 Driver Version: 555.99 CUDA Version: 12.5 | |-----------------------------------------+------------------------+----------------------+ | 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 GeForce RTX 4080 ... On | 00000000:01:00.0 On | N/A | | 35% 34C P8 21W / 320W | 2025MiB / 16376MiB | 2% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 1 C /python3.11 N/A | +-----------------------------------------------------------------------------------------+ # ```
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No labels
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#1576