per-device capability probe: pre-Ada GPUs auto-fall back to upcast path

fp8_scaled_mm: clear sm_89+ gate (RTX 30-series lacks fp8 cores)

harden pipeline dtype derivation against fp8 params (2 sites)

harden pipeline dtype derivation against fp8 params

fix: scaled-mm swap ran on META model (0 linears matched); branch on weight dtype at call time

torch._scaled_mm fp8 Linear forward (measured x2.8 kernel / x1.5 e2e vs bf16 on RTX 5090)

QuantizationPolicy.fp8_scaled_mm_torch (torch-native, no tensorrt_llm)

FIX: memory bank trim was a no-op when max_size<=num_fix_frames (tail[-0:] returns whole list) -> bank grew unbounded

LoRA fusion: map kohya-FLATTENED keys (lora_unet_*, dots->underscores) onto model paths via exact flat-key lookup - such LoRAs previously matched zero keys

LoRA hardening: kohya lora_down/up support + alpha scaling, fuse telemetry + zero-match warning, refuse comfy_quant checkpoints with clear error; lora_file dropdown

Upload 11 files