Tarjei Mandt ca14d3d835 Fix sharding of quantized models with non-power-of-2 bits (#3006)

2026-01-18 07:21:56 -08:00

..

mlx

Fix sharding of quantized models with non-power-of-2 bits (#3006)

2026-01-18 07:21:56 -08:00

src

Expose to/from fp8 in Python and don't auto-convert fp8 when loading from safetensors (#2985)

2026-01-13 15:48:21 -08:00

tests

Fix sharding of quantized models with non-power-of-2 bits (#3006)

2026-01-18 07:21:56 -08:00