Skip to content

ggml : fix RWKV ops thread assignment#21226

Merged
ggerganov merged 1 commit intomasterfrom
gg/ggml-fix-rwkv-threads
Apr 1, 2026
Merged

ggml : fix RWKV ops thread assignment#21226
ggerganov merged 1 commit intomasterfrom
gg/ggml-fix-rwkv-threads

Conversation

@ggerganov
Copy link
Copy Markdown
Member

Overview

fix ggml-org/ggml#1450

The logic was incorrectly handling nth > HEADS.

Additional information

Requirements

@github-actions github-actions Bot added the ggml changes relating to the ggml tensor library for machine learning label Mar 31, 2026
@ckastner
Copy link
Copy Markdown
Collaborator

ckastner commented Mar 31, 2026

I'm not experienced enough to review this particular change, but I can confirm that it fixes the test for me.

@ggerganov ggerganov merged commit d43375f into master Apr 1, 2026
45 of 46 checks passed
@ggerganov ggerganov deleted the gg/ggml-fix-rwkv-threads branch April 1, 2026 08:10
slartibardfast pushed a commit to slartibardfast/llama.cpp that referenced this pull request Apr 12, 2026
Seunghhon pushed a commit to Seunghhon/llama.cpp that referenced this pull request Apr 26, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ggml changes relating to the ggml tensor library for machine learning

Projects

None yet

Development

Successfully merging this pull request may close these issues.

CPU backend: test-backend-ops deadlocks on RWKV_WKV6 with 33+ threads

2 participants