github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #3725] [CLOSED] Add env override for opts.NumThread & opts.NumGPU #21807

New Issue
Closed
opened 2026-04-19 15:52:47 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-19 15:52:47 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/3725
Author: @ghost
Created: 4/18/2024
Status: ❌ Closed

Base: main ← Head: llm-threads-gpu-layers-env-override

📝 Commits (3)

  • 9517c00 Add env override for opts.NumThread & opts.NumGPU
  • 6ddfd4d Merge branch 'main' into llm-threads-gpu-layers-env-override
  • 9940f43 Conform logging to surrounding implementation

📊 Changes

2 files changed (+35 additions, -5 deletions)

View changed files

📝 cmd/cmd.go (+7 -5)
📝 llm/server.go (+28 -0)

📄 Description

This enables the capability to limit or disable both NumThread & NumGPU which can be useful for testing and running multiple concurrent instances. NumThread limitation is also valuable to reliably enforce core affinity (as with taskset) on hybrid architectures like modern Intel & ARM.

  • OLLAMA_MAX_LLM_THREADS Maximum number of LLM CPU threads (default is unlimited: 0)
  • OLLAMA_MAX_GPU_LAYERS Maximum number of GPU layers (default is unlimited: -1)

🔄 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/3725 **Author:** [@ghost](https://github.com/ghost) **Created:** 4/18/2024 **Status:** ❌ Closed **Base:** `main` ← **Head:** `llm-threads-gpu-layers-env-override` --- ### 📝 Commits (3) - [`9517c00`](https://github.com/ollama/ollama/commit/9517c00bfd1c1da59df0801a7b17f4c60506c01a) Add env override for opts.NumThread & opts.NumGPU - [`6ddfd4d`](https://github.com/ollama/ollama/commit/6ddfd4d743b1eff2d3aebc37b7916db4a7dee885) Merge branch 'main' into llm-threads-gpu-layers-env-override - [`9940f43`](https://github.com/ollama/ollama/commit/9940f43cd6fdfe93b3f27d54464612f0af99d0bb) Conform logging to surrounding implementation ### 📊 Changes **2 files changed** (+35 additions, -5 deletions) <details> <summary>View changed files</summary> 📝 `cmd/cmd.go` (+7 -5) 📝 `llm/server.go` (+28 -0) </details> ### 📄 Description This enables the capability to limit or disable both `NumThread` & `NumGPU` which can be useful for testing and running multiple concurrent instances. `NumThread` limitation is also valuable to reliably enforce core affinity (as with `taskset`) on hybrid architectures like modern Intel & ARM. - `OLLAMA_MAX_LLM_THREADS` **Maximum number of LLM CPU threads (default is unlimited: 0)** - `OLLAMA_MAX_GPU_LAYERS` **Maximum number of GPU layers (default is unlimited: -1)** --- <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 2026-04-19 15:52:47 -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#21807
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?