github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.5k Packages Projects Releases 122 Wiki Activity

[PR #5556] [CLOSED] feat: Support Moore Threads GPU #11826

New Issue
Closed
opened 2026-04-12 23:39:52 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 23:39:52 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/5556
Author: @yeahdongcn
Created: 7/9/2024
Status: ❌ Closed

Base: main ← Head: musa

📝 Commits (4)

  • 8aec5fe Support Moore Threads GPU
  • e0dda32 Update gen_linux.sh to support MUSA
  • 18d3826 Support docker build for MUSA
  • ab2fd84 Add doc for Moore Threads GPU

📊 Changes

15 files changed (+488 additions, -14 deletions)

View changed files

📝 Dockerfile (+33 -1)
📝 discover/gpu.go (+21 -1)
📝 discover/gpu_test.go (+1 -1)
➕ discover/musa_common.go (+22 -0)
➕ discover/musa_linux.go (+257 -0)
➕ discover/musa_windows.go (+14 -0)
📝 discover/types.go (+7 -0)
📝 docs/docker.md (+23 -0)
📝 docs/gpu.md (+18 -2)
📝 envconfig/config.go (+2 -0)
📝 llm/generate/gen_linux.sh (+48 -0)
📝 llm/server.go (+1 -0)
📝 runners/common.go (+1 -1)
📝 scripts/build_docker.sh (+10 -8)
➕ scripts/ubuntu_linux_deps.sh (+30 -0)

📄 Description

Moore Threads, a cutting-edge GPU startup, introduces MUSA (Moore Threads Unified System Architecture) as its foundational technology. This pull request marks the initial integration of MTGPU support into Ollama, leveraging MUSA's capabilities to enhance LLM inference performance.

I also sent a PR to llama.cpp to integrate MTGPU.

Tested models are:

NAME                    ID              SIZE    MODIFIED     
mistral:latest          2ae6f6dd7a3d    4.1 GB  22 hours ago
llama3:8b-instruct-fp16 c666fe422df7    16 GB   30 hours ago
qwen2:72b               14066dfa503f    41 GB   2 days ago  
nomic-embed-text:latest 0a109f422b47    274 MB  2 days ago  
llama3:latest           365c0bd3c000    4.7 GB  3 days ago  
tinyllama:latest        2644915ede35    637 MB  3 days ago

Screenshot:

Screenshot 2024-10-29 at 09 30 46

🔄 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/5556 **Author:** [@yeahdongcn](https://github.com/yeahdongcn) **Created:** 7/9/2024 **Status:** ❌ Closed **Base:** `main` ← **Head:** `musa` --- ### 📝 Commits (4) - [`8aec5fe`](https://github.com/ollama/ollama/commit/8aec5fe5a38fef98429e85c90ed705e77d1f94b3) Support Moore Threads GPU - [`e0dda32`](https://github.com/ollama/ollama/commit/e0dda326201c90e9a9711c78eeb7a727ac4d83b4) Update gen_linux.sh to support MUSA - [`18d3826`](https://github.com/ollama/ollama/commit/18d3826170e1507d566193176e3da7d63ee7a10f) Support docker build for MUSA - [`ab2fd84`](https://github.com/ollama/ollama/commit/ab2fd8434043bc2bd3ada4baed0d94d8496e6d26) Add doc for Moore Threads GPU ### 📊 Changes **15 files changed** (+488 additions, -14 deletions) <details> <summary>View changed files</summary> 📝 `Dockerfile` (+33 -1) 📝 `discover/gpu.go` (+21 -1) 📝 `discover/gpu_test.go` (+1 -1) ➕ `discover/musa_common.go` (+22 -0) ➕ `discover/musa_linux.go` (+257 -0) ➕ `discover/musa_windows.go` (+14 -0) 📝 `discover/types.go` (+7 -0) 📝 `docs/docker.md` (+23 -0) 📝 `docs/gpu.md` (+18 -2) 📝 `envconfig/config.go` (+2 -0) 📝 `llm/generate/gen_linux.sh` (+48 -0) 📝 `llm/server.go` (+1 -0) 📝 `runners/common.go` (+1 -1) 📝 `scripts/build_docker.sh` (+10 -8) ➕ `scripts/ubuntu_linux_deps.sh` (+30 -0) </details> ### 📄 Description [Moore Threads](https://en.mthreads.com/), a cutting-edge GPU startup, introduces MUSA (Moore Threads Unified System Architecture) as its foundational technology. This pull request marks the initial integration of MTGPU support into Ollama, leveraging MUSA's capabilities to enhance LLM inference performance. I also sent a [PR](https://github.com/ggerganov/llama.cpp/pull/8383) to [llama.cpp](https://github.com/ggerganov/llama.cpp) to integrate MTGPU. Tested models are: ```bash NAME ID SIZE MODIFIED mistral:latest 2ae6f6dd7a3d 4.1 GB 22 hours ago llama3:8b-instruct-fp16 c666fe422df7 16 GB 30 hours ago qwen2:72b 14066dfa503f 41 GB 2 days ago nomic-embed-text:latest 0a109f422b47 274 MB 2 days ago llama3:latest 365c0bd3c000 4.7 GB 3 days ago tinyllama:latest 2644915ede35 637 MB 3 days ago ``` Screenshot: <img width="1392" alt="Screenshot 2024-10-29 at 09 30 46" src="https://github.com/user-attachments/assets/1203fe66-9692-4099-8b32-973ee37cb3b0"> --- <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 23:39:52 -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#11826
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?