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 #7063] Support setting num_ctx in openai api via extra query parameter #66542

New Issue
Open
opened 2026-05-04 07:19:48 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 07:19:48 -05:00
Owner
Copy Link

Originally created by @fzyzcjy on GitHub (Oct 1, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7063

Hi thanks for the package! It would be great if num_ctx can be set in openai api. It seems openai api allows extra query parameter, and other packages like vllm can make use of it to support custom args.

Originally created by @fzyzcjy on GitHub (Oct 1, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7063 Hi thanks for the package! It would be great if num_ctx can be set in openai api. It seems openai api allows extra query parameter, and other packages like vllm can make use of it to support custom args.
GiteaMirror added the feature requestapi labels 2026-05-04 07:20:31 -05:00
GiteaMirror commented 2026-05-04 07:20:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 1, 2024):

https://github.com/ollama/ollama/pull/6504

<!-- gh-comment-id:2386325381 --> @rick-github commented on GitHub (Oct 1, 2024): https://github.com/ollama/ollama/pull/6504
GiteaMirror commented 2026-05-04 07:20:37 -05:00
Author
Owner
Copy Link

@TomLucidor commented on GitHub (Nov 21, 2024):

Need something similar to this (when model supports extra large context window) but for ollama serve parameter as well so that is won't be stuck at 2048. https://github.com/ollama/ollama/issues/6286

Weirdly enough the issue of context and generation sizes are complex

<!-- gh-comment-id:2490023153 --> @TomLucidor commented on GitHub (Nov 21, 2024): Need something similar to this (when model supports extra large context window) but for `ollama serve` parameter as well so that is won't be stuck at 2048. https://github.com/ollama/ollama/issues/6286 Weirdly enough the issue of context and generation sizes are complex - Flexible context window https://github.com/ollama/ollama/issues/1005 https://github.com/ollama/ollama/issues/1964 - Stop generation once limit is reached https://github.com/ollama/ollama/issues/3355 - RAM-based (or VRAM-based) context size adjustments https://github.com/ollama/ollama/issues/7629
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 api 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#66542
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?