github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4093] 使用本地知识库时模型每次都要重新加载 #2542

New Issue
Closed
opened 2026-04-12 12:51:59 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 12:51:59 -05:00
Owner
Copy Link

Originally created by @androidsr on GitHub (May 2, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4093

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

执行对话，查询本地向量库，将查询到的结果和问题一并发给模型处理。查询出来的文本并不大或者没有。此时模型处理时会很慢。查看显卡内存情况。显示的重新加载了对话模型。

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

0.1.32

Originally created by @androidsr on GitHub (May 2, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4093 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? 执行对话，查询本地向量库，将查询到的结果和问题一并发给模型处理。查询出来的文本并不大或者没有。此时模型处理时会很慢。查看显卡内存情况。显示的重新加载了对话模型。 ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version 0.1.32
GiteaMirror added the bug label 2026-04-12 12:51:59 -05:00
GiteaMirror commented 2026-04-12 12:51:59 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (May 2, 2024):

You can use the keep_alive parameter to change how long models stay loaded. https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-keep-a-model-loaded-in-memory-or-make-it-unload-immediately

If you're trying to load multiple models in your use-case, 0.1.33 adds concurrency support as an experimental feature which you can turn on with OLLAMA_MAX_LOADED_MODELS. https://github.com/ollama/ollama/releases

<!-- gh-comment-id:2091167235 --> @dhiltgen commented on GitHub (May 2, 2024): You can use the `keep_alive` parameter to change how long models stay loaded. https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-keep-a-model-loaded-in-memory-or-make-it-unload-immediately If you're trying to load multiple models in your use-case, 0.1.33 adds concurrency support as an experimental feature which you can turn on with OLLAMA_MAX_LOADED_MODELS. https://github.com/ollama/ollama/releases
GiteaMirror commented 2026-04-12 12:51:59 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 9, 2024):

Yes as mentioned by @dhiltgen OLLAMA_MAX_LOADED_MODELS will be 0 default soon, meaning Ollama will support loading multiple models. This will allow you to run both a language and an embedding model side by side.

To use this today, set OLLAMA_MAX_LOADED_MODELS:

OLLAMA_MAX_LOADED_MODELS=0 ollama serve
<!-- gh-comment-id:2103436447 --> @jmorganca commented on GitHub (May 9, 2024): Yes as mentioned by @dhiltgen `OLLAMA_MAX_LOADED_MODELS` will be 0 default soon, meaning Ollama will support loading multiple models. This will allow you to run both a language and an embedding model side by side. To use this today, set `OLLAMA_MAX_LOADED_MODELS`: ``` OLLAMA_MAX_LOADED_MODELS=0 ollama serve ```
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#2542
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?