github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #7624] [MERGED] runner.go: Make KV entry accounting more robust #59168

New Issue
Closed
opened 2026-04-29 14:04:21 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-29 14:04:21 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/7624
Author: @jessegross
Created: 11/12/2024
Status: ✅ Merged
Merged: 11/12/2024
Merged by: @jessegross

Base: main ← Head: jessegross/kv_shift

📝 Commits (1)

  • b039afd runner.go: Make KV entry accounting more robust

📊 Changes

2 files changed (+58 additions, -56 deletions)

View changed files

📝 llama/runner/cache.go (+33 -12)
📝 llama/runner/runner.go (+25 -44)

📄 Description

The structure of the accounting for KV cache shifting was carried over from the old runner but it now doesn't feel natural with the new runner. There are a number of invariants that should hold true but are difficult to reason about. There is at least one bug report that would imply that the invariants are not holding.

This reduces the number of implicit assumptions and is more forgiving of unexpected situations. It also improves behavior around which input tokens are kept when truncation occurs.

Bug #7545

🔄 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/7624 **Author:** [@jessegross](https://github.com/jessegross) **Created:** 11/12/2024 **Status:** ✅ Merged **Merged:** 11/12/2024 **Merged by:** [@jessegross](https://github.com/jessegross) **Base:** `main` ← **Head:** `jessegross/kv_shift` --- ### 📝 Commits (1) - [`b039afd`](https://github.com/ollama/ollama/commit/b039afdd969f794b1f89e101b4c04ddafc352b0a) runner.go: Make KV entry accounting more robust ### 📊 Changes **2 files changed** (+58 additions, -56 deletions) <details> <summary>View changed files</summary> 📝 `llama/runner/cache.go` (+33 -12) 📝 `llama/runner/runner.go` (+25 -44) </details> ### 📄 Description The structure of the accounting for KV cache shifting was carried over from the old runner but it now doesn't feel natural with the new runner. There are a number of invariants that should hold true but are difficult to reason about. There is at least one bug report that would imply that the invariants are not holding. This reduces the number of implicit assumptions and is more forgiving of unexpected situations. It also improves behavior around which input tokens are kept when truncation occurs. Bug #7545 --- <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 14:04:21 -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#59168
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?