Add KV cache quantization to mlx_lm.server (#1043)#1476

katlun-lgtm wants to merge 1 commit into

ml-explore:mainml-explore/mlx-lm:mainfrom

katlun-lgtm:feat/server-kv-cache-quantkatlun-lgtm/mlx-lm:feat/server-kv-cache-quantCopy head branch name to clipboard