ollama/kvcache
Jesse Gross 73d6a82cce ollamarunner: Memory usage reporting
This provides granular information about the backend memory allocations
required by the runner:
 - Per backend
 - Per layer
 - Weights, cache and graph
 - Allocation status

This can be used for debugging and validating memory estimates.
2025-05-22 14:38:09 -07:00
..
cache.go ollamarunner: Preallocate worst case graph at startup 2025-04-08 10:01:28 -07:00
causal.go kvcache: Log batch size if we can't find a slot 2025-05-01 16:26:36 -07:00
causal_test.go ollamarunner: Memory usage reporting 2025-05-22 14:38:09 -07:00
encoder.go ollamarunner: Preallocate worst case graph at startup 2025-04-08 10:01:28 -07:00
wrapper.go ollamarunner: Preallocate worst case graph at startup 2025-04-08 10:01:28 -07:00