github-starred/ollama-ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-03-11 20:23:55 -05:00
Code Issues 2.2k Packages Projects Releases 100 Wiki Activity

[PR #11561] [MERGED] kvcache: Don't shift empty batches #12318

New Issue
Closed
opened 2025-11-12 16:33:19 -06:00 by GiteaMirror · 0 comments
GiteaMirror commented 2025-11-12 16:33:19 -06:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/11561
Author: @jessegross
Created: 7/28/2025
Status: ✅ Merged
Merged: 7/29/2025
Merged by: @jessegross

Base: main ← Head: jessegross/shift

📝 Commits (1)

  • dd7c90e kvcache: Don't shift empty batches

📊 Changes

1 file changed (+17 additions, -4 deletions)

View changed files

📝 kvcache/causal.go (+17 -4)

📄 Description

When we context shift, we delete half the context and apply RoPE with an offset to the other half. We used to RoPE across the entire context in a single pass with a zero offset for the deleted section. With the change to shifting in batches, we can skip any batches where all of the offsets would be zero. This typically reduces the number of operations by half.

🔄 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/11561 **Author:** [@jessegross](https://github.com/jessegross) **Created:** 7/28/2025 **Status:** ✅ Merged **Merged:** 7/29/2025 **Merged by:** [@jessegross](https://github.com/jessegross) **Base:** `main` ← **Head:** `jessegross/shift` --- ### 📝 Commits (1) - [`dd7c90e`](https://github.com/ollama/ollama/commit/dd7c90e530574f05d15ce3ba51ecaddd2ec1047c) kvcache: Don't shift empty batches ### 📊 Changes **1 file changed** (+17 additions, -4 deletions) <details> <summary>View changed files</summary> 📝 `kvcache/causal.go` (+17 -4) </details> ### 📄 Description When we context shift, we delete half the context and apply RoPE with an offset to the other half. We used to RoPE across the entire context in a single pass with a zero offset for the deleted section. With the change to shifting in batches, we can skip any batches where all of the offsets would be zero. This typically reduces the number of operations by half. --- <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 2025-11-12 16:33:19 -06:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
client2
cloud
compatibility
context-length
create
docker
documentation
embeddings
engine
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
install
integration
intel
js
linux
macos
memory
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
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-ollama#12318
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?