github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #8092] [MERGED] llama: Ensure KV cache is fully defragmented. #43869

New Issue
Closed
opened 2026-04-24 23:26:14 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-24 23:26:14 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/8092
Author: @jessegross
Created: 12/14/2024
Status: ✅ Merged
Merged: 12/17/2024
Merged by: @jessegross

Base: main ← Head: jessegross/defrag

📝 Commits (1)

  • 6126c4d llama: Ensure KV cache is fully defragmented.

📊 Changes

3 files changed (+289 additions, -61 deletions)

View changed files

📝 llama/llama.cpp (+46 -53)
➕ llama/patches/0014-llama-Ensure-KV-cache-is-fully-defragmented.patch (+242 -0)
📝 llama/runner/runner.go (+1 -8)

📄 Description

Sometimes the KV cache requires defragmentation even without triggering the threshold heuristic. In this case, decoding will not being able to find a KV cache slot. This is particularly difficult for the caller to handle if it happens in between ubatches. To avoid this, we should immediately trigger a defrag.

In addition, a heavily fragmented cache can require more than max_moves to defragment. Currently, we stop when we hit the limit but this can leave a cache that still does not have adequate space even after defragmentation is triggered. Instead, we should do multiple batches of processing until everything is complete.

Fixes #7949

I also plan to send this patch upstream to llama.cpp.

🔄 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/8092 **Author:** [@jessegross](https://github.com/jessegross) **Created:** 12/14/2024 **Status:** ✅ Merged **Merged:** 12/17/2024 **Merged by:** [@jessegross](https://github.com/jessegross) **Base:** `main` ← **Head:** `jessegross/defrag` --- ### 📝 Commits (1) - [`6126c4d`](https://github.com/ollama/ollama/commit/6126c4d5fe97ead823b785dee8cf1b09eb37544b) llama: Ensure KV cache is fully defragmented. ### 📊 Changes **3 files changed** (+289 additions, -61 deletions) <details> <summary>View changed files</summary> 📝 `llama/llama.cpp` (+46 -53) ➕ `llama/patches/0014-llama-Ensure-KV-cache-is-fully-defragmented.patch` (+242 -0) 📝 `llama/runner/runner.go` (+1 -8) </details> ### 📄 Description Sometimes the KV cache requires defragmentation even without triggering the threshold heuristic. In this case, decoding will not being able to find a KV cache slot. This is particularly difficult for the caller to handle if it happens in between ubatches. To avoid this, we should immediately trigger a defrag. In addition, a heavily fragmented cache can require more than max_moves to defragment. Currently, we stop when we hit the limit but this can leave a cache that still does not have adequate space even after defragmentation is triggered. Instead, we should do multiple batches of processing until everything is complete. Fixes #7949 I also plan to send this patch upstream to llama.cpp. --- <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 2026-04-24 23:26:14 -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#43869
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?