github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #11906] [MERGED] test: improve scheduler/concurrency stress tests #18921

New Issue
Closed
opened 2026-04-16 06:51:51 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-16 06:51:51 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/11906
Author: @dhiltgen
Created: 8/14/2025
Status: ✅ Merged
Merged: 8/15/2025
Merged by: @dhiltgen

Base: main ← Head: integration

📝 Commits (3)

  • 5aaaf95 test: improve scheduler/concurrency stress tests
  • 2f845ff test: add parallel generate with history
  • 2e7e983 test: focus embed tests on embedding models

📊 Changes

4 files changed (+167 additions, -228 deletions)

View changed files

📝 integration/concurrency_test.go (+95 -182)
📝 integration/context_test.go (+50 -0)
📝 integration/testdata/embed.json (+7 -16)
📝 integration/utils_test.go (+15 -30)

📄 Description

The scheduler test used to use approximate memory figures and would often over or under shoot a systems capcity leading to flaky test results. This should improve the reliability of this scenario by leveraging ps output to determinie exactly how many models it takes to trigger thrashing.

The concurrency test is also refined to target num_parallel + 1 and handle timeouts better.

With these refinements, TestMultiModelConcurrency was redundant

Also added a new TestGenerateWithHistory to exercise parallel requests with history context to ensure cache behavior

Focus embeddings tests on embedding models

🔄 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/11906 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 8/14/2025 **Status:** ✅ Merged **Merged:** 8/15/2025 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `integration` --- ### 📝 Commits (3) - [`5aaaf95`](https://github.com/ollama/ollama/commit/5aaaf95a2188a60a661005ff9f961a302883b170) test: improve scheduler/concurrency stress tests - [`2f845ff`](https://github.com/ollama/ollama/commit/2f845ffb98b48e9ac53e9bec6063ce3fd92044b7) test: add parallel generate with history - [`2e7e983`](https://github.com/ollama/ollama/commit/2e7e98350c6802fb570e8fa7ad1626adb965f741) test: focus embed tests on embedding models ### 📊 Changes **4 files changed** (+167 additions, -228 deletions) <details> <summary>View changed files</summary> 📝 `integration/concurrency_test.go` (+95 -182) 📝 `integration/context_test.go` (+50 -0) 📝 `integration/testdata/embed.json` (+7 -16) 📝 `integration/utils_test.go` (+15 -30) </details> ### 📄 Description The scheduler test used to use approximate memory figures and would often over or under shoot a systems capcity leading to flaky test results. This should improve the reliability of this scenario by leveraging ps output to determinie exactly how many models it takes to trigger thrashing. The concurrency test is also refined to target num_parallel + 1 and handle timeouts better. With these refinements, TestMultiModelConcurrency was redundant Also added a new TestGenerateWithHistory to exercise parallel requests with history context to ensure cache behavior Focus embeddings tests on embedding models --- <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 06:51:51 -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#18921
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?