Pinned Loading
-
-
-
-
etl-solved
etl-solved PublicETL fails in the same ways every time. Those ways are enumerable. Enumerated problems are solvable.
Python
-
gpu-kernel
gpu-kernel PublicMeasurement-first toolkit for pushing local LLM inference on Apple M-series GPUs toward the hardware's actual limits.
Python
-
slipstream
slipstream PublicRun a 35B MoE on a MacBook in ~2 GB of RAM: experts streamed from SSD, near-roofline Metal kernels, and a KV cache that reloads from disk instead of re-prefilling
Swift
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.