On Apple Silicon, `vram_state` is set to `VRAMState.SHARED` because
CPU and GPU share unified memory. However, `text_encoder_device()`
only checked for `HIGH_VRAM` and `NORMAL_VRAM`, causing all text
encoders to fall back to CPU on MPS devices.
Adding `VRAMState.SHARED` to the condition allows non-quantized text
encoders (e.g. bf16 Gemma 3 12B) to run on the MPS GPU, providing
significant speedup for text encoding and prompt generation.
Note: quantized models (fp4/fp8) that use float8_e4m3fn internally
will still fall back to CPU via the `supports_cast()` check in
`CLIP.__init__()`, since MPS does not support fp8 dtypes.
Anton Bukov
b941913f1d