github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9749] Feature Request: Enforce Fixed num_ctx Parameter to Optimize Model Loading Performance #68426

New Issue
Closed
opened 2026-05-04 13:55:32 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-04 13:55:32 -05:00
Owner
Copy Link

Originally created by @mlibre on GitHub (Mar 14, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9749

Hey,

Currently, while the OLLAMA_CONTEXT_LENGTH environment variable sets a default context window size, clients can override this by specifying the num_ctx parameter in API requests. This flexibility can lead to performance issues, especially when Ollama is used as a code assistance server. Different extensions specifying varying num_ctx values cause Ollama to unload and reload the same model with different context sizes, resulting in significant delays and a sluggish user experience.

I am proposing the addition of a new environment variable like OLLAMA_FIXED_CONTEXT_LENGTH, to ignore num_ctx value across all client requests

Originally created by @mlibre on GitHub (Mar 14, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9749 Hey, Currently, while the `OLLAMA_CONTEXT_LENGTH` environment variable sets a default context window size, clients can override this by specifying the `num_ctx` parameter in API requests. This flexibility can lead to performance issues, especially when Ollama is used as a code assistance server. Different extensions specifying varying `num_ctx` values cause Ollama to unload and reload the same model with different context sizes, resulting in significant delays and a sluggish user experience. I am proposing the addition of a new environment variable like `OLLAMA_FIXED_CONTEXT_LENGTH`, to ignore `num_ctx` value across all client requests
GiteaMirror added the feature request label 2026-05-04 13:55:33 -05:00
GiteaMirror commented 2026-05-04 13:55:38 -05:00
Author
Owner
Copy Link

@nickthecook commented on GitHub (May 28, 2025):

This would be useful.

The Ollama server knows how much VRAM is available. Every client app shouldn't need to. This should be set and enforced in Ollama.

<!-- gh-comment-id:2917135769 --> @nickthecook commented on GitHub (May 28, 2025): This would be useful. The Ollama server knows how much VRAM is available. Every client app shouldn't need to. This should be set and enforced in Ollama.
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#68426
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?