Pins that supports_cast() lets fp8-capable devices skip the quantized
text encoder fallback (these run on non-MPS CI too), that low vram
states still place text encoders on the CPU, and adds bf16 placement,
dict-form (full checkpoint) state dicts, and non-tensor state dict
entries to the MPS tests.
On Apple Silicon vram_state is VRAMState.SHARED (unified memory), but
text_encoder_device() only returned the GPU for HIGH_VRAM/NORMAL_VRAM,
so text encoders ran on the CPU. For LM-style encoders like ACE-Step
1.5 the text encode stage dominates generation time on Mac.
This re-lands #12809, which was reverted in #13070 because it broke
quantized text encoders on Mac: the MPS backend cannot cast float8
dtypes (pytorch/pytorch#132624), and the existing supports_cast()
fallback in CLIP.__init__ only inspects declared model dtypes, which
never reflect fp8 weights behind comfy_quant quantization metadata
(QuantizedTensor reports the compute dtype, not the fp8 storage dtype).
To keep quantized text encoders working, CLIP.__init__ now decides the
device before any weights are allocated: it checks supports_cast() on
the resolved dtype, and when the load device cannot cast fp8 it scans
the incoming state dict for fp8 tensors or comfy_quant markers and
keeps those text encoders on the offload device. Devices that can cast
fp8 (cuda etc.) skip the scan entirely. The pre-existing shift-back
path now also updates the current device so the load log stays
accurate.
Adds MPS unit tests: fp16 placement on the GPU, fp8 fallback via
declared dtype, secondary dtype (dtype_llama style), state-dict fp8
weights, and comfy_quant markers, plus a canary that fails when a
torch release adds fp8 casts on MPS so the fallback can be relaxed.
