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 #13350] [MERGED] ggml: handle all streams #19444

New Issue
Closed
opened 2026-04-16 07:07:38 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-16 07:07:38 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/13350
Author: @dhiltgen
Created: 12/5/2025
Status: ✅ Merged
Merged: 12/6/2025
Merged by: @dhiltgen

Base: main ← Head: ggml_bump_followup

📝 Commits (1)

📊 Changes

6 files changed (+55 additions, -35 deletions)

View changed files

📝 llama/patches/0020-ggml-No-alloc-mode.patch (+26 -16)
📝 llama/patches/0022-ggml-Enable-resetting-backend-devices.patch (+4 -4)
📝 llama/patches/0024-GPU-discovery-enhancements.patch (+7 -7)
📝 llama/patches/0029-ggml-cuda-skip-large-batches.patch (+2 -2)
📝 ml/backend/ggml/ggml/src/ggml-cuda/common.cuh (+8 -4)
📝 ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu (+8 -2)

📄 Description

Follow up from #12992

Free all streams, and keep the alloc logic aligned across streams.

🔄 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/13350 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 12/5/2025 **Status:** ✅ Merged **Merged:** 12/6/2025 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `ggml_bump_followup` --- ### 📝 Commits (1) - [`8d908eb`](https://github.com/ollama/ollama/commit/8d908eb31b9c1a86a288da42b7661ede1cc7f09c) ggml: handle all streams ### 📊 Changes **6 files changed** (+55 additions, -35 deletions) <details> <summary>View changed files</summary> 📝 `llama/patches/0020-ggml-No-alloc-mode.patch` (+26 -16) 📝 `llama/patches/0022-ggml-Enable-resetting-backend-devices.patch` (+4 -4) 📝 `llama/patches/0024-GPU-discovery-enhancements.patch` (+7 -7) 📝 `llama/patches/0029-ggml-cuda-skip-large-batches.patch` (+2 -2) 📝 `ml/backend/ggml/ggml/src/ggml-cuda/common.cuh` (+8 -4) 📝 `ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu` (+8 -2) </details> ### 📄 Description Follow up from #12992 Free all streams, and keep the alloc logic aligned across streams. --- <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 07:07:38 -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#19444
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?