github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 05:36:16 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[PR #7158] [MERGED] runner.go: Handle truncation of tokens for stop sequences #12335

New Issue
Closed
opened 2026-04-12 23:55:52 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 23:55:52 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/7158
Author: @jessegross
Created: 10/10/2024
Status: ✅ Merged
Merged: 10/10/2024
Merged by: @jessegross

Base: main ← Head: jessegross/bug7153

📝 Commits (2)

  • 2d23bed server: Don't clear cmd when closing a server
  • f2999a8 runner.go: Handle truncation of tokens for stop sequences

📊 Changes

4 files changed (+64 additions, -35 deletions)

View changed files

📝 llama/runner/runner.go (+20 -7)
📝 llama/runner/stop.go (+6 -4)
📝 llama/runner/stop_test.go (+35 -23)
📝 llm/server.go (+3 -1)

📄 Description

When a single token contains both text to be return and a stop sequence, this causes an out of bounds error when we update the cache to match our text. This is because we currently assume that the removing the stop sequence will consume at least one token.

This also inverts the logic to deal with positive numbers, rather than a value to be subtracted, which is easier to reason about.

🔄 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/7158 **Author:** [@jessegross](https://github.com/jessegross) **Created:** 10/10/2024 **Status:** ✅ Merged **Merged:** 10/10/2024 **Merged by:** [@jessegross](https://github.com/jessegross) **Base:** `main` ← **Head:** `jessegross/bug7153` --- ### 📝 Commits (2) - [`2d23bed`](https://github.com/ollama/ollama/commit/2d23bede70299a51c627be0f045cdd0b12d62a13) server: Don't clear cmd when closing a server - [`f2999a8`](https://github.com/ollama/ollama/commit/f2999a822939633520facb5877b856242c49c9eb) runner.go: Handle truncation of tokens for stop sequences ### 📊 Changes **4 files changed** (+64 additions, -35 deletions) <details> <summary>View changed files</summary> 📝 `llama/runner/runner.go` (+20 -7) 📝 `llama/runner/stop.go` (+6 -4) 📝 `llama/runner/stop_test.go` (+35 -23) 📝 `llm/server.go` (+3 -1) </details> ### 📄 Description When a single token contains both text to be return and a stop sequence, this causes an out of bounds error when we update the cache to match our text. This is because we currently assume that the removing the stop sequence will consume at least one token. This also inverts the logic to deal with positive numbers, rather than a value to be subtracted, which is easier to reason about. --- <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 2026-04-12 23:55:52 -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#12335
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?