github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #9634] [CLOSED] server: allow running embed models in parallel #18290

New Issue
Closed
opened 2026-04-16 06:30:59 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-16 06:30:59 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/9634
Author: @BruceMacD
Created: 3/10/2025
Status: ❌ Closed

Base: main ← Head: brucemacd/parallel-embed-models

📝 Commits (1)

  • 12a8b00 server: allow running embed models in parallel

📊 Changes

1 file changed (+0 additions, -5 deletions)

View changed files

📝 server/sched.go (+0 -5)

📄 Description

The ability to run embedding models in parallel with other types of models was removed due to limitations in server slot loading in a past version of the server. This slot loading system is no longer used, and embedding models can run in parallel with chat models.

Without running embedding and chat models in parallel doing retrieval-augmented-generation can be much slower. As the chat model will need to be unloaded from memory before the embedding model can be run, and then reloaded when a chat request is sent.

Original PR for this bug, for reference: https://github.com/ollama/ollama/pull/6467

🔄 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/9634 **Author:** [@BruceMacD](https://github.com/BruceMacD) **Created:** 3/10/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `brucemacd/parallel-embed-models` --- ### 📝 Commits (1) - [`12a8b00`](https://github.com/ollama/ollama/commit/12a8b00b34dfd64b3f59234b3ae4d0ba4a0e0937) server: allow running embed models in parallel ### 📊 Changes **1 file changed** (+0 additions, -5 deletions) <details> <summary>View changed files</summary> 📝 `server/sched.go` (+0 -5) </details> ### 📄 Description The ability to run embedding models in parallel with other types of models was removed due to limitations in server slot loading in a past version of the server. This slot loading system is no longer used, and embedding models can run in parallel with chat models. Without running embedding and chat models in parallel doing retrieval-augmented-generation can be much slower. As the chat model will need to be unloaded from memory before the embedding model can be run, and then reloaded when a chat request is sent. Original PR for this bug, for reference: https://github.com/ollama/ollama/pull/6467 --- <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 2026-04-16 06:30:59 -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#18290
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?