Skip to content

ggml: Check the right iface method before using the fallback 2d get#23514

Merged
CISC merged 1 commit into
ggml-org:masterfrom
dskwe:fix-get-tensor-2d-async-iface-check
May 23, 2026
Merged

ggml: Check the right iface method before using the fallback 2d get#23514
CISC merged 1 commit into
ggml-org:masterfrom
dskwe:fix-get-tensor-2d-async-iface-check

Conversation

@dskwe
Copy link
Copy Markdown
Contributor

@dskwe dskwe commented May 22, 2026

Overview

Same oversight as #23306 but for the async (backend-based) path.

Additional information

ggml_backend_tensor_get_2d_async was checking set_tensor_2d_async instead of get_tensor_2d_async, and the bounds assertion said "write" when it should say "read".

Let me know if this fix is appropriate, or if there's a better way to handle this.

Requirements

  • I have read and agree with the contributing guidelines
  • AI usage disclosure: NO

@github-actions github-actions Bot added the ggml changes relating to the ggml tensor library for machine learning label May 22, 2026
@CISC CISC merged commit a497476 into ggml-org:master May 23, 2026
49 checks passed
spiritbuun pushed a commit to spiritbuun/buun-llama-cpp that referenced this pull request May 25, 2026
@jesseposner jesseposner mentioned this pull request May 27, 2026
fewtarius pushed a commit to fewtarius/llama.cpp that referenced this pull request May 30, 2026
turbo-tan pushed a commit to turbo-tan/llama.cpp-tq3 that referenced this pull request Jun 2, 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.

3 participants