github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #9746] [MERGED] server/internal/client: use chunksums for concurrent blob verification #44299

New Issue
Closed
opened 2026-04-24 23:48:06 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-24 23:48:06 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/9746
Author: @bmizerany
Created: 3/13/2025
Status: ✅ Merged
Merged: 3/14/2025
Merged by: @bmizerany

Base: main ← Head: bmizerany/chunksums

📝 Commits (1)

  • 0ad94c4 server/internal/client: use chunksums for concurrent blob verification

📊 Changes

8 files changed (+433 additions, -283 deletions)

View changed files

📝 server/internal/cache/blob/cache.go (+22 -32)
➕ server/internal/cache/blob/chunked.go (+66 -0)
📝 server/internal/cache/blob/digest.go (+4 -0)
📝 server/internal/chunks/chunks.go (+10 -7)
📝 server/internal/client/ollama/registry.go (+198 -154)
📝 server/internal/client/ollama/registry_test.go (+3 -1)
📝 server/internal/registry/server.go (+98 -69)
📝 server/internal/registry/server_test.go (+32 -20)

📄 Description

Replace large-chunk blob downloads with parallel small-chunk verification to solve timeout and performance issues. Registry users experienced progressively slowing download speeds as large-chunk transfers aged, often timing out completely.

The previous approach downloaded blobs in a few large chunks but required a separate, single-threaded pass to read the entire blob back from disk for verification after download completion.

This change uses the new chunksums API to fetch many smaller chunk+digest pairs, allowing concurrent downloads and immediate verification as each chunk arrives. Chunks are written directly to their final positions, eliminating the entire separate verification pass.

The result is more reliable downloads that maintain speed throughout the transfer process and significantly faster overall completion, especially over unstable connections or with large blobs.

🔄 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/9746 **Author:** [@bmizerany](https://github.com/bmizerany) **Created:** 3/13/2025 **Status:** ✅ Merged **Merged:** 3/14/2025 **Merged by:** [@bmizerany](https://github.com/bmizerany) **Base:** `main` ← **Head:** `bmizerany/chunksums` --- ### 📝 Commits (1) - [`0ad94c4`](https://github.com/ollama/ollama/commit/0ad94c4b8ef837020bd58cac06118bb10489b315) server/internal/client: use chunksums for concurrent blob verification ### 📊 Changes **8 files changed** (+433 additions, -283 deletions) <details> <summary>View changed files</summary> 📝 `server/internal/cache/blob/cache.go` (+22 -32) ➕ `server/internal/cache/blob/chunked.go` (+66 -0) 📝 `server/internal/cache/blob/digest.go` (+4 -0) 📝 `server/internal/chunks/chunks.go` (+10 -7) 📝 `server/internal/client/ollama/registry.go` (+198 -154) 📝 `server/internal/client/ollama/registry_test.go` (+3 -1) 📝 `server/internal/registry/server.go` (+98 -69) 📝 `server/internal/registry/server_test.go` (+32 -20) </details> ### 📄 Description Replace large-chunk blob downloads with parallel small-chunk verification to solve timeout and performance issues. Registry users experienced progressively slowing download speeds as large-chunk transfers aged, often timing out completely. The previous approach downloaded blobs in a few large chunks but required a separate, single-threaded pass to read the entire blob back from disk for verification after download completion. This change uses the new chunksums API to fetch many smaller chunk+digest pairs, allowing concurrent downloads and immediate verification as each chunk arrives. Chunks are written directly to their final positions, eliminating the entire separate verification pass. The result is more reliable downloads that maintain speed throughout the transfer process and significantly faster overall completion, especially over unstable connections or with large blobs. --- <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 23:48:06 -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#44299
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?