github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-23 06:01:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[PR #15020] fix: preserve partial chunk progress before returning fatal download errors #77266

New Issue
Open
opened 2026-05-05 09:56:15 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-05 09:56:15 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/15020
Author: @jasonkwh
Created: 3/23/2026
Status: 🔄 Open

Base: main ← Head: fix/preserve-chunk-progress-on-download-error

📝 Commits (1)

  • e6bba88 server: preserve chunk progress to disk before rolling back on fatal download errors

📊 Changes

1 file changed (+6 additions, -5 deletions)

View changed files

📝 server/download.go (+6 -5)

📄 Description

Problem

When downloadChunk encountered a fatal error (e.g. unexpected network failure), it rolled back b.Completed and returned immediately without saving the bytes already received to the part file. On the next retry, the chunk would restart from the beginning, wasting bandwidth — particularly costly for large model files.

Fix

Move part.Completed.Add(n) and writePart before the fatal error check so partial progress is always flushed to disk first. The b.Completed rollback is kept for fatal errors to maintain an accurate global progress counter, but the chunk bytes are no longer discarded.

🔄 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/15020 **Author:** [@jasonkwh](https://github.com/jasonkwh) **Created:** 3/23/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `fix/preserve-chunk-progress-on-download-error` --- ### 📝 Commits (1) - [`e6bba88`](https://github.com/ollama/ollama/commit/e6bba886012aa2cea57e2301faced594f1e43872) server: preserve chunk progress to disk before rolling back on fatal download errors ### 📊 Changes **1 file changed** (+6 additions, -5 deletions) <details> <summary>View changed files</summary> 📝 `server/download.go` (+6 -5) </details> ### 📄 Description ## Problem When `downloadChunk` encountered a fatal error (e.g. unexpected network failure), it rolled back `b.Completed` and returned immediately without saving the bytes already received to the part file. On the next retry, the chunk would restart from the beginning, wasting bandwidth — particularly costly for large model files. ## Fix Move `part.Completed.Add(n)` and `writePart` before the fatal error check so partial progress is always flushed to disk first. The `b.Completed` rollback is kept for fatal errors to maintain an accurate global progress counter, but the chunk bytes are no longer discarded. --- <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 2026-05-05 09:56:15 -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#77266
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?