github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #1642] [MERGED] Add Cache option #1573 #57332

New Issue
Closed
opened 2026-04-29 11:54:50 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-29 11:54:50 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/1642
Author: @K0IN
Created: 12/20/2023
Status: ✅ Merged
Merged: 12/22/2023
Merged by: @BruceMacD

Base: main ← Head: main

📝 Commits (1)

📊 Changes

3 files changed (+6 additions, -2 deletions)

View changed files

📝 api/types.go (+2 -0)
📝 docs/api.md (+2 -1)
📝 llm/ext_server.go (+2 -1)

📄 Description

This PR, adds the API option "cache", that allows the llama.cpp server to cache our prompt Eval and the response.
This speed-up follow-up calls immensely for some models, if you use it over the API, with the same prompt (or even partial ones), it will speed up subsequent calls, since it skips the evaluation of the prompt.

Also, this PR includes commands /set cache and /set nocache to give users the ability to enable prompt caching in the official CLI.

  • Add a new entry "cache" to the options object that is passed to the worker
  • Add commands /set cache and /set nocache to allow this in the repl cli
  • Update docs

This is a partial fix for, Enable prompt cache #1573, we might need to patch llama.cpp at some point to allow us full flexibility.

🔄 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/1642 **Author:** [@K0IN](https://github.com/K0IN) **Created:** 12/20/2023 **Status:** ✅ Merged **Merged:** 12/22/2023 **Merged by:** [@BruceMacD](https://github.com/BruceMacD) **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (1) - [`504497f`](https://github.com/ollama/ollama/commit/504497ffbcac44596f083ad14ee3d99b24b62996) Add Cache flag to api ### 📊 Changes **3 files changed** (+6 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `api/types.go` (+2 -0) 📝 `docs/api.md` (+2 -1) 📝 `llm/ext_server.go` (+2 -1) </details> ### 📄 Description This PR, adds the API option "cache", that allows the llama.cpp server to cache our prompt Eval and the response. This speed-up follow-up calls immensely for some models, if you use it over the API, with the same prompt (or even partial ones), it will speed up subsequent calls, since it skips the evaluation of the prompt. Also, this PR includes commands /set cache and /set nocache to give users the ability to enable prompt caching in the official CLI. * Add a new entry "cache" to the options object that is passed to the worker * Add commands /set cache and /set nocache to allow this in the repl cli * Update docs This is a partial fix for, Enable prompt cache #1573, we might need to patch llama.cpp at some point to allow us full flexibility. --- <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 2026-04-29 11:54:50 -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#57332
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?