Jesse Gross f66216e399 ggml: Support heterogeneous KV cache layer sizes in memory estimation hace 1 mes
..
llm_darwin.go cd5c8f6471 Optimize container images for startup (#6547) hace 7 meses
llm_linux.go cd5c8f6471 Optimize container images for startup (#6547) hace 7 meses
llm_windows.go dbba73469d runner: Set windows above normal priority (#6905) hace 7 meses
memory.go f66216e399 ggml: Support heterogeneous KV cache layer sizes in memory estimation hace 1 mes
memory_test.go f66216e399 ggml: Support heterogeneous KV cache layer sizes in memory estimation hace 1 mes
server.go f66216e399 ggml: Support heterogeneous KV cache layer sizes in memory estimation hace 1 mes
server_test.go 2ddc32d5c5 llm: do not error on "null" format (#8139) hace 4 meses
status.go 909a88c5c0 Improve crash reporting (#7728) hace 5 meses