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 #15135] feat: add experimental WebGPU backend stub documentation #20316

New Issue
Open
opened 2026-04-16 07:33:03 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-16 07:33:03 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/15135
Author: @harshitgavita-07
Created: 3/29/2026
Status: 🔄 Open

Base: main ← Head: feature/webgpu-stub

📝 Commits (2)

  • 627085a docs: add experimental WebGPU backend stub documentation
  • 505e636 feat: add no‑op think tool for structured reasoning

📊 Changes

2 files changed (+69 additions, -0 deletions)

View changed files

➕ docs/webgpu-stub.md (+24 -0)
➕ x/tools/think.go (+45 -0)

📄 Description

This PR adds a minimal stub documentation for an experimental WebGPU backend. It outlines goals, design sketch, and next steps for contributors to implement a real WebGPU‑accelerated inference provider.

@jmorganca, I think this could be a fun entry point for the community to explore GPU‑offload possibilities. If you like the direction, I’d be happy to help flesh out the actual provider implementation or sponsor a small hack‑session to get it rolling.

What’s included

  • docs/webgpu-stub.md – a concise design document and roadmap.
  • Clear steps for contributors to add the Go provider, health‑check, UI toggle, and tests.

Next steps

  • Implement the Go source (ackend/provider/webgpu.go).
  • Register the provider under the ID webgpu.
  • Add UI settings for enabling the endpoint.
  • Write unit tests.

Looking forward to your thoughts!

🔄 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/15135 **Author:** [@harshitgavita-07](https://github.com/harshitgavita-07) **Created:** 3/29/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `feature/webgpu-stub` --- ### 📝 Commits (2) - [`627085a`](https://github.com/ollama/ollama/commit/627085ab0cf88266e7cb4c9f5904c4c74d721006) docs: add experimental WebGPU backend stub documentation - [`505e636`](https://github.com/ollama/ollama/commit/505e63606624b26526d6a67d2a685be4963e0031) feat: add no‑op think tool for structured reasoning ### 📊 Changes **2 files changed** (+69 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `docs/webgpu-stub.md` (+24 -0) ➕ `x/tools/think.go` (+45 -0) </details> ### 📄 Description This PR adds a minimal stub documentation for an experimental WebGPU backend. It outlines goals, design sketch, and next steps for contributors to implement a real WebGPU‑accelerated inference provider. @jmorganca, I think this could be a fun entry point for the community to explore GPU‑offload possibilities. If you like the direction, I’d be happy to help flesh out the actual provider implementation or sponsor a small hack‑session to get it rolling. **What’s included** - docs/webgpu-stub.md – a concise design document and roadmap. - Clear steps for contributors to add the Go provider, health‑check, UI toggle, and tests. **Next steps** - Implement the Go source (ackend/provider/webgpu.go). - Register the provider under the ID webgpu. - Add UI settings for enabling the endpoint. - Write unit tests. Looking forward to your thoughts! --- <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 2026-04-16 07:33:03 -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#20316
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?