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 #814] [CLOSED] ROCm support #41588

New Issue
Closed
opened 2026-04-24 21:26:39 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-24 21:26:39 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/814
Author: @65a
Created: 10/17/2023
Status: ❌ Closed

Base: main ← Head: main

📝 Commits (1)

  • 33a0f7c Use build tags to generate accelerated binaries for CUDA and ROCm on Linux.

📊 Changes

10 files changed (+264 additions, -59 deletions)

View changed files

📝 Dockerfile (+4 -2)
📝 Dockerfile.build (+2 -2)
📝 README.md (+33 -2)
➕ llm/accelerator_cuda.go (+67 -0)
➕ llm/accelerator_none.go (+21 -0)
➕ llm/accelerator_rocm.go (+85 -0)
📝 llm/llama.cpp/generate_linux.go (+0 -7)
➕ llm/llama.cpp/generate_linux_cuda.go (+24 -0)
➕ llm/llama.cpp/generate_linux_rocm.go (+25 -0)
📝 llm/llama.go (+3 -46)

📄 Description

#667 got closed during a bad rebase attempt. This should be just about the minimum I can come up with to use build tags to switch between ROCm and CUDA, as well as docs for how to build it. The existing dockerfiles are updated so they do not break.

Please let me know @jmorganca @mxyng @BruceMacD if you'd like this in a different approach or something, or if you don't want to do this. Closes #738. Will post test results for GGML and GGUF files.

🔄 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/814 **Author:** [@65a](https://github.com/65a) **Created:** 10/17/2023 **Status:** ❌ Closed **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (1) - [`33a0f7c`](https://github.com/ollama/ollama/commit/33a0f7c3032f3d59d37f29b4f07f67af8736b28f) Use build tags to generate accelerated binaries for CUDA and ROCm on Linux. ### 📊 Changes **10 files changed** (+264 additions, -59 deletions) <details> <summary>View changed files</summary> 📝 `Dockerfile` (+4 -2) 📝 `Dockerfile.build` (+2 -2) 📝 `README.md` (+33 -2) ➕ `llm/accelerator_cuda.go` (+67 -0) ➕ `llm/accelerator_none.go` (+21 -0) ➕ `llm/accelerator_rocm.go` (+85 -0) 📝 `llm/llama.cpp/generate_linux.go` (+0 -7) ➕ `llm/llama.cpp/generate_linux_cuda.go` (+24 -0) ➕ `llm/llama.cpp/generate_linux_rocm.go` (+25 -0) 📝 `llm/llama.go` (+3 -46) </details> ### 📄 Description #667 got closed during a bad rebase attempt. This should be just about the minimum I can come up with to use build tags to switch between ROCm and CUDA, as well as docs for how to build it. The existing dockerfiles are updated so they do not break. Please let me know @jmorganca @mxyng @BruceMacD if you'd like this in a different approach or something, or if you don't want to do this. Closes #738. Will post test results for GGML and GGUF files. --- <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 21:26:39 -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#41588
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?