ollama/runner/ollamarunner
Jesse Gross 13d497db4c
ollamarunner: Temporarily disable worst case graph preallocation
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
2025-12-29 06:37:46 -06:00
..
cache.go kvcache: Add check for values that fall out of sliding window cache 2025-04-02 11:55:48 -07:00
cache_test.go ollamarunner: Preallocate worst case graph at startup 2025-04-08 10:01:28 -07:00
runner.go ollamarunner: Temporarily disable worst case graph preallocation 2025-12-29 06:37:46 -06:00