The engine reports its cells: llama_memory_cell_usage, GET /cells, POST /v1/chat/completions/cells - #92

The engine reports its cells: llama_memory_cell_usage, GET /cells, POST /v1/chat/completions/cells#92

joelteply merged 3 commits into

889580fc/seq-state-across-stream-countsCambrianTech/llama.cpp:889580fc/seq-state-across-stream-countsfrom

fable/cell-usageCambrianTech/llama.cpp:fable/cell-usageCopy head branch name to clipboard