[PR #10480] ollamarunner: Temporarily disable worst case graph preallocation #13253

Closed
opened 2026-04-13 00:22:07 -05:00 by GiteaMirror · 0 comments
Owner

Original Pull Request: https://github.com/ollama/ollama/pull/10480

State: closed
Merged: Yes


When we later have a large batch running purely on a CPU, this results the error:
GGML_ASSERT(talloc->buffer_id >= 0)

Disabling this means that we will incrementally reallocate memory as the graph grows.

Fixes #10410

**Original Pull Request:** https://github.com/ollama/ollama/pull/10480 **State:** closed **Merged:** Yes --- When we later have a large batch running purely on a CPU, this results the error: GGML_ASSERT(talloc->buffer_id >= 0) Disabling this means that we will incrementally reallocate memory as the graph grows. Fixes #10410
GiteaMirror added the pull-request label 2026-04-13 00:22:08 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#13253