github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #7174] [MERGED] llm: Remove GGML_CUDA_NO_PEER_COPY for ROCm #43586

New Issue
Closed
opened 2026-04-24 23:11:46 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-24 23:11:46 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/7174
Author: @dhiltgen
Created: 10/11/2024
Status: ✅ Merged
Merged: 10/12/2024
Merged by: @dhiltgen

Base: main ← Head: rocm_small_ram

📝 Commits (1)

  • f80f65f llm: Remove GGML_CUDA_NO_PEER_COPY for ROCm

📊 Changes

2 files changed (+1 additions, -2 deletions)

View changed files

📝 llm/generate/gen_linux.sh (+1 -1)
📝 llm/generate/gen_windows.ps1 (+0 -1)

📄 Description

This workaround logic in llama.cpp is causing crashes for users with less system memory than VRAM.

The original change adding this was meant to resolve gibberish responses on multi-GPU radeon setups. I'll focus my testing on that to see if I see any regressions, and if not, drop the draft status.

Fixes #6756

🔄 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/7174 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 10/11/2024 **Status:** ✅ Merged **Merged:** 10/12/2024 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `rocm_small_ram` --- ### 📝 Commits (1) - [`f80f65f`](https://github.com/ollama/ollama/commit/f80f65f2e9e2cade88cc733e69438688c5c14455) llm: Remove GGML_CUDA_NO_PEER_COPY for ROCm ### 📊 Changes **2 files changed** (+1 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `llm/generate/gen_linux.sh` (+1 -1) 📝 `llm/generate/gen_windows.ps1` (+0 -1) </details> ### 📄 Description This workaround logic in llama.cpp is causing crashes for users with less system memory than VRAM. The original change adding this was meant to resolve gibberish responses on multi-GPU radeon setups. I'll focus my testing on that to see if I see any regressions, and if not, drop the draft status. Fixes #6756 --- <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 2026-04-24 23:11:46 -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#43586
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?