sm_120 sa3-m: add the fp8 medium-DiT tier (176 fp8 GEMM + 96 bf16 fused MHA, 1.43-1.95x vs fp16mixed)

sa3-m fp8: calibrated dit_fp8.onnx (real-conditioning activation + per-channel weight scales, @ryanontheinside #47; refs unchanged dit_fp8lin.onnx.data)

sa3-m fp8: ship calibrated-bakedmin engine (176 fp8 GEMM + 96 bf16 fused MHA + baked fp32 RoPE; calibration by @ryanontheinside #47)

sm_120 SAME-L: AOT (graph-capturable) engines + tensorRT/README.md (#6)

Upload onnx/sa3-m/dit_fp8lin.onnx.data with huggingface_hub

Upload onnx/sa3-m/dit_fp8.onnx with huggingface_hub

Upload tensorRT/sm_90/sa3-m/dit_fp8.trt with huggingface_hub

Fix the bf16 medium DiT: bake RoPE's tables into the graph (clipping 3.112% -> 0.014%) (#5)

Rebuild medium DiT fp16-mixed engines (sm_90 + new sm_120): attention now fuses, 4.3x faster (#4)

Fix medium DiT FP16-mixed ONNX: bound the RoPE island so attention fuses (4.3x faster, cos 1.0000) (#3)

Add MLX base-model DiT weights for LoRA training (#2)

Add bf16 medium DiT TRT engine (sm_90) — FMHA-fused, medium default (#1)

tflite: replace naive same-l/enc_w8a8-dyn.tflite with GPTQ (torch-free, real-audio calibrated)

tflite: replace naive same-l/enc_w8a32.tflite with GPTQ (torch-free, real-audio calibrated)

tflite: replace naive same-s/enc_w8a8-dyn.tflite with GPTQ (torch-free, real-audio calibrated)

tflite: replace naive same-s/enc_w8a32.tflite with GPTQ (torch-free, real-audio calibrated)

tflite: add same-l/enc_w8a8-dyn.tflite (quantized encoder, varlen)

tflite: add same-l/enc_w8a32.tflite (quantized encoder, varlen)

tflite: add same-l/enc_w16a32.tflite (quantized encoder, varlen)

tflite: add same-s/enc_w8a8-dyn.tflite (quantized encoder, varlen)

tflite: add same-s/enc_w8a32.tflite (quantized encoder, varlen)

tflite: add same-s/enc_w16a32.tflite (quantized encoder, varlen)

tflite: add sa3-m/dit_w16a32.tflite (quantized, varlen+varbatch)

tflite: add sa3-m/dit_w8a32.tflite (quantized, varlen+varbatch)

tflite: add sa3-m/dit_w8a8-dyn.tflite (quantized, varlen+varbatch)

tflite: add same-l/dec_w16a32.tflite (quantized, varlen+varbatch)

tflite: add sa3-sm-sfx/dit_w16a32.tflite (quantized, varlen+varbatch)

tflite: add sa3-sm-music/dit_w16a32.tflite (quantized, varlen+varbatch)

tflite: add same-l/dec_w8a32.tflite (quantized, varlen+varbatch)

tflite: add same-l/dec_w8a8-dyn.tflite (quantized, varlen+varbatch)

tflite: add sa3-sm-sfx/dit_w8a32.tflite (quantized, varlen+varbatch)

tflite: add sa3-sm-music/dit_w8a32.tflite (quantized, varlen+varbatch)

tflite: add sa3-sm-sfx/dit_w8a8-dyn.tflite (quantized, varlen+varbatch)

tflite: add sa3-sm-music/dit_w8a8-dyn.tflite (quantized, varlen+varbatch)

tflite: add same-s/dec_w16a32.tflite (quantized, varlen+varbatch)

tflite: add same-s/dec_w8a32.tflite (quantized, varlen+varbatch)

tflite: add same-s/dec_w8a8-dyn.tflite (quantized, varlen+varbatch)

varbatch DiT: dynamic batch axis (bit-exact at batch=1; enables batched CFG at batch=2)

varbatch DiT: dynamic batch axis (bit-exact at batch=1; enables batched CFG at batch=2)

varbatch DiT: dynamic batch axis (bit-exact at batch=1; enables batched CFG at batch=2)

Upload tflite/README.md with huggingface_hub

Upload tflite/t5gemma/encoder_fp16.tflite with huggingface_hub

Upload tflite/same-l/dec_fp32.tflite with huggingface_hub

Upload tflite/same-l/enc_fp32.tflite with huggingface_hub

Upload tflite/same-s/dec_fp32.tflite with huggingface_hub

Upload tflite/same-s/enc_fp32.tflite with huggingface_hub

Upload tflite/sa3-sm-sfx/dit_fp32.tflite with huggingface_hub

Upload tflite/sa3-m/dit_fp32.tflite with huggingface_hub

Upload tflite/sa3-sm-music/dit_fp32.tflite with huggingface_hub

Fix missing 2π factor in seconds_freqs across all dit.onnx (FP32 source ONNX)