github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8904] Suggestion: Ollama community can try using the dosubot robot. #5773

New Issue
Open
opened 2026-04-12 17:06:30 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 17:06:30 -05:00
Owner
Copy Link

Originally created by @tigflanker on GitHub (Feb 7, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8904

I have seen other communities use the dosubot robot in their Issues section. It appears that it can build a knowledge base based on the community’s source code and historical Issues.
After a user poses a question, dosubot will first provide a tentative answer, which is very effective for those “already answered but not found” questions.

Here is a case: example
This is the website for dosubot: https://github.com/apps/dosubot

Additionally, I would like to ask a question😂: I have a total of 4 T4 GPUs (0, 1, 2, 3), each with 16GB of memory. When I load a model (20GB), according to the original strategy, it will be evenly distributed across the 4 GPUs. I am concerned that this division might increase unnecessary data communication. Is there a way to make it load only onto the last two GPUs? Just like:

curl -X POST http://localhost:11434/api/chat \
-H "Content-Type: application/json" \
-d '{"model": "deepseek-r1:32b", "keep_alive": -1, "options":{"num_gpu": 2, "gpu_ids": "2,3"}}'
Originally created by @tigflanker on GitHub (Feb 7, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8904 I have seen other communities use the dosubot robot in their Issues section. It appears that it can build a knowledge base based on the community’s source code and historical Issues. After a user poses a question, dosubot will first provide a tentative answer, which is very effective for those “already answered but not found” questions. Here is a case: [example](https://github.com/langgenius/dify/issues/13013) This is the website for dosubot: https://github.com/apps/dosubot ---------- Additionally, I would like to ask a question😂: I have a total of 4 T4 GPUs (0, 1, 2, 3), each with 16GB of memory. When I load a model (20GB), according to the original strategy, it will be evenly distributed across the 4 GPUs. I am concerned that this division might increase unnecessary data communication. Is there a way to make it load only onto the last two GPUs? Just like: ``` curl -X POST http://localhost:11434/api/chat \ -H "Content-Type: application/json" \ -d '{"model": "deepseek-r1:32b", "keep_alive": -1, "options":{"num_gpu": 2, "gpu_ids": "2,3"}}' ```
GiteaMirror added the feature request label 2026-04-12 17:06:30 -05:00
GiteaMirror commented 2026-04-12 17:06:31 -05:00
Author
Owner
Copy Link

@tigflanker commented on GitHub (Feb 7, 2025):

It appears that using dosubot is advantageous for both project maintainers and users. It can play the role of a DAG, helping maintainers to “pre-process” some issues where users haven’t found the key information.

<!-- gh-comment-id:2641808941 --> @tigflanker commented on GitHub (Feb 7, 2025): It appears that using dosubot is advantageous for both project maintainers and users. It can play the role of a DAG, helping maintainers to “pre-process” some issues where users haven’t found the key information.
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 feature request
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#5773
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?