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 #13244] ggml: Use max graph memory allocation when reserving #24671

New Issue
Open
opened 2026-04-19 17:43:48 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-19 17:43:48 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/13244
Author: @jessegross
Created: 11/26/2025
Status: 🔄 Open

Base: main ← Head: jessegross/multi_chunk_reserve

📝 Commits (1)

  • f03b8bc ggml: Use max graph memory allocation when reserving

📊 Changes

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

View changed files

📝 ml/backend/ggml/ggml.go (+6 -6)

📄 Description

When calculating the size of the memory required for a compute graph, we may test multiple graphs - for example a vision encoder and the text model. Since these graphs are never run at the same time, we just want the max size.

Typically, a new graph only reallocates memory if it doesn't fit in the existing space, so the last graph reservation is the max size. However, the Vulkan backend imposes a 1G cap for a single allocation, which means that the graph may require multiple allocations. This results in a problem if:

  • There is an old graph with one small chunk and one big chunk
  • A new graph with one big chunk that is smaller than the total of the old graph. In this case, the big chunk of the new graph will trigger a reallocation, which will free the old second chunk. The total amount of memory reported will be lower than the max. To avoid this, we should explicitly take the max from each graph.

🔄 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/13244 **Author:** [@jessegross](https://github.com/jessegross) **Created:** 11/26/2025 **Status:** 🔄 Open **Base:** `main` ← **Head:** `jessegross/multi_chunk_reserve` --- ### 📝 Commits (1) - [`f03b8bc`](https://github.com/ollama/ollama/commit/f03b8bc51afa14fabd06412a16b27ee53d45b664) ggml: Use max graph memory allocation when reserving ### 📊 Changes **1 file changed** (+6 additions, -6 deletions) <details> <summary>View changed files</summary> 📝 `ml/backend/ggml/ggml.go` (+6 -6) </details> ### 📄 Description When calculating the size of the memory required for a compute graph, we may test multiple graphs - for example a vision encoder and the text model. Since these graphs are never run at the same time, we just want the max size. Typically, a new graph only reallocates memory if it doesn't fit in the existing space, so the last graph reservation is the max size. However, the Vulkan backend imposes a 1G cap for a single allocation, which means that the graph may require multiple allocations. This results in a problem if: - There is an old graph with one small chunk and one big chunk - A new graph with one big chunk that is smaller than the total of the old graph. In this case, the big chunk of the new graph will trigger a reallocation, which will free the old second chunk. The total amount of memory reported will be lower than the max. To avoid this, we should explicitly take the max from each graph. --- <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 17:43:48 -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#24671
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?