github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #5922] [MERGED] Introduce GPU Overhead env var #11964

New Issue
Closed
opened 2026-04-12 23:44:16 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 23:44:16 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/5922
Author: @dhiltgen
Created: 7/24/2024
Status: ✅ Merged
Merged: 9/5/2024
Merged by: @dhiltgen

Base: main ← Head: gpu_overhead

📝 Commits (1)

  • cde1aa9 Introduce GPU Overhead env var

📊 Changes

3 files changed (+28 additions, -3 deletions)

View changed files

📝 cmd/cmd.go (+1 -0)
📝 envconfig/config.go (+20 -0)
📝 llm/memory.go (+7 -3)

📄 Description

Provide a mechanism for users to set aside an amount of VRAM on each GPU to make room for other applications they want to start after Ollama, or workaround memory prediction bugs

Concurrency and multi-GPU support made the older OLLAMA_MAX_VRAM setting untenable (many users have multi-GPU setups with different sizes of VRAM) so this was removed in #5855 This new setting uses an "overhead" value so we can subtract that from the reported Free space on each GPU for more reasonable/consistent results.

      OLLAMA_GPU_OVERHEAD        Reserve a portion of VRAM per GPU (bytes)

🔄 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/5922 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 7/24/2024 **Status:** ✅ Merged **Merged:** 9/5/2024 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `gpu_overhead` --- ### 📝 Commits (1) - [`cde1aa9`](https://github.com/ollama/ollama/commit/cde1aa9e2fb13358aa991d599b22f841e6ca932b) Introduce GPU Overhead env var ### 📊 Changes **3 files changed** (+28 additions, -3 deletions) <details> <summary>View changed files</summary> 📝 `cmd/cmd.go` (+1 -0) 📝 `envconfig/config.go` (+20 -0) 📝 `llm/memory.go` (+7 -3) </details> ### 📄 Description Provide a mechanism for users to set aside an amount of VRAM on each GPU to make room for other applications they want to start after Ollama, or workaround memory prediction bugs Concurrency and multi-GPU support made the older `OLLAMA_MAX_VRAM` setting untenable (many users have multi-GPU setups with different sizes of VRAM) so this was removed in #5855 This new setting uses an "overhead" value so we can subtract that from the reported Free space on each GPU for more reasonable/consistent results. ``` OLLAMA_GPU_OVERHEAD Reserve a portion of VRAM per GPU (bytes) ``` --- <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 23:44:16 -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#11964
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?