verifiedhigh · 0.95updated 2026-10-03

MLX-LM server CLI source

repo

Fields

sources/engine-mlx-lm-server

URL

https://github.com/ml-explore/mlx-lm/blob/main/mlx_lm/server.py

Publisher

ml-explore

Kind

repo

Accessed

2026-10-03

notes

mlx_lm/server.py CLI source. Direct evidence for the batching flags (--decode-concurrency, --prompt-concurrency) and that --kv-bits disables batching.

Notes

mlx_lm/server.py CLI source. Direct evidence for the batching flags (--decode-concurrency, --prompt-concurrency) and that --kv-bits disables batching.

Cross-references

This record references no other records.