[PR #15431] mlx: faster model push with chunking #25693

Open
opened 2026-04-19 18:21:37 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/15431
Author: @dhiltgen
Created: 4/8/2026
Status: 🔄 Open

Base: mainHead: push_st


📝 Commits (1)

  • fd01033 mlx: faster model push with chunking

📊 Changes

3 files changed (+1444 additions, -24 deletions)

View changed files

📝 x/imagegen/transfer/transfer.go (+6 -0)
📝 x/imagegen/transfer/transfer_test.go (+1138 -2)
📝 x/imagegen/transfer/upload.go (+300 -22)

📄 Description

Use the same pattern we do for GGUF blob upload for large safetensor blobs so we can get faster throughput on uploads.


🔄 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/15431 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 4/8/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `push_st` --- ### 📝 Commits (1) - [`fd01033`](https://github.com/ollama/ollama/commit/fd01033e94f345006df34371c62a513dd72b6e07) mlx: faster model push with chunking ### 📊 Changes **3 files changed** (+1444 additions, -24 deletions) <details> <summary>View changed files</summary> 📝 `x/imagegen/transfer/transfer.go` (+6 -0) 📝 `x/imagegen/transfer/transfer_test.go` (+1138 -2) 📝 `x/imagegen/transfer/upload.go` (+300 -22) </details> ### 📄 Description Use the same pattern we do for GGUF blob upload for large safetensor blobs so we can get faster throughput on uploads. --- <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 2026-04-19 18:21:37 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#25693