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

[PR #11042] [CLOSED] server: model info caching system for improved performance #44668

New Issue
Closed
opened 2026-04-25 00:16:57 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-25 00:16:57 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/11042
Author: @BruceMacD
Created: 6/10/2025
Status: ❌ Closed

Base: main ← Head: brucemacd/cache-models

📝 Commits (5)

  • 883f655 server: model info caching system for improved performance
  • 2348fef Revert "server: model info caching system for improved performance"
  • 8d51d92 server: cache gguf model capabilities rather than reading off disc
  • 63e7634 pr feedback
  • f2a4d05 gofmt

📊 Changes

5 files changed (+344 additions, -185 deletions)

View changed files

➕ server/cache/capabilities.go (+115 -0)
➕ server/cache/capabilities_test.go (+211 -0)
📝 server/images.go (+6 -53)
📝 server/images_test.go (+0 -125)
📝 server/routes.go (+12 -7)

📄 Description

Implements an in-memory cache for model capabilities rather than reading them off disc every time. The goal here is to enable adding model capabilities to ollama ls while still being fast.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/11042 **Author:** [@BruceMacD](https://github.com/BruceMacD) **Created:** 6/10/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `brucemacd/cache-models` --- ### 📝 Commits (5) - [`883f655`](https://github.com/ollama/ollama/commit/883f655dd6e33d923026606902d8b81eccd0fc71) server: model info caching system for improved performance - [`2348fef`](https://github.com/ollama/ollama/commit/2348fef5688be867d44d1e56cf882d467a3e1a37) Revert "server: model info caching system for improved performance" - [`8d51d92`](https://github.com/ollama/ollama/commit/8d51d92f3b97e98f9c7fa4c8cc4d6b13cfc4e390) server: cache gguf model capabilities rather than reading off disc - [`63e7634`](https://github.com/ollama/ollama/commit/63e7634014c0f12536dc77583d2dc9f36e499024) pr feedback - [`f2a4d05`](https://github.com/ollama/ollama/commit/f2a4d058f9d723fc11bbffcb5e579505a3c19be6) gofmt ### 📊 Changes **5 files changed** (+344 additions, -185 deletions) <details> <summary>View changed files</summary> ➕ `server/cache/capabilities.go` (+115 -0) ➕ `server/cache/capabilities_test.go` (+211 -0) 📝 `server/images.go` (+6 -53) 📝 `server/images_test.go` (+0 -125) 📝 `server/routes.go` (+12 -7) </details> ### 📄 Description Implements an in-memory cache for model capabilities rather than reading them off disc every time. The goal here is to enable adding model capabilities to `ollama ls` while still being fast. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-25 00:16:57 -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 pull-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#44668
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?