- Austin, TX
- www.asianefficiency.com
- @runsonai
- humanrouter
Popular repositories Loading
-
ddtree-mlx
ddtree-mlx PublicTree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive. First MLX port with custom Metal kernels for hybrid model support.
-
calendar-availability-textexpander
calendar-availability-textexpander PublicTextExpander snippet that pastes your Google Calendar availability with one keystroke
Python 1
-
-
spark-vllm-docker
spark-vllm-docker PublicForked from eugr/spark-vllm-docker
Docker configuration for running VLLM on dual DGX Sparks
Shell
-
mlx-ddtree-failed
mlx-ddtree-failed PublicDDTree speculative decoding for Qwen 3.5/3.6 on Apple Silicon — what we tried and why raw inference still wins
Python
If the problem persists, check the GitHub status page or contact support.

