github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8842] non global OLLAMA_NUM_PARALLEL #52240

New Issue
Open
opened 2026-04-28 22:36:41 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-28 22:36:41 -05:00
Owner
Copy Link

Originally created by @Robinsane on GitHub (Feb 5, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8842

Hello

First of all, I love Ollama, all contributors are doing a lovely job, Thank you!

When setting OLLAMA_NUM_PARALLEL to 2, this means LLM's will be able to handle 2 requests at the same time.
This then means double the (V)RAM is required, since there can be 2 different contexts at the same time.

My issue is the following:
For some models, I'd like to configure OLLAMA_NUM_PARALLEL = 2 .
At the same time, I'd like models with huge context windows to work sequentially only, so that I don't need an extra e.g. 16 - 64 GB for a context window that's barely / never used.

Thank you for your time reading this feature request ^.^

Originally created by @Robinsane on GitHub (Feb 5, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8842 Hello First of all, I love Ollama, all contributors are doing a lovely job, Thank you! When setting OLLAMA_NUM_PARALLEL to 2, this means LLM's will be able to handle 2 requests at the same time. This then means double the (V)RAM is required, since there can be 2 different contexts at the same time. My issue is the following: For some models, I'd like to configure OLLAMA_NUM_PARALLEL = 2 . At the same time, I'd like models with huge context windows to work sequentially only, so that I don't need an extra e.g. 16 - 64 GB for a context window that's barely / never used. Thank you for your time reading this feature request ^.^
GiteaMirror added the feature request label 2026-04-28 22:36:41 -05:00
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#52240
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?