Tagged "omlx"
4 articles tagged omlx, 14 April 2026 to 8 November 2026. Newest first.
-
OMLX: Distributed Prefill Acceleration Across Multiple Macs for 2.9x Speedup
OMLX enables Mac users to leverage a second machine for LLM prefill operations, achieving 2.9x acceleration for local inference. This distributed computing approach brings cost-effective multi-device optimization to the Apple Silicon ecosystem.
-
OMLX: Use a Second Mac to Speed Up Local LLM Prefill 2.9x
OMLX enables distributed prefill acceleration across multiple Apple Silicon Macs, achieving 2.9x speedup by offloading the prefill phase to a secondary device—opening new possibilities for local multi-device inference.
-
DFlash Doubles Token Generation Speed of Qwen3.5 27B on Mac M5 Max
New DFlash support in oMLX 0.3.5 RC1 achieves 2x speedup for Qwen3.5 27B inference on Apple Silicon, reaching 22 T/S from 9 T/S using speculative decoding with draft models.
-
oMLX Framework Implements DFlash Attention for Optimized Inference
The oMLX framework has added DFlash attention implementation, improving inference efficiency on local hardware. This update represents progress in core optimization techniques for on-device LLM execution.