Add Buy Me a Coffee support link (buymeacoffee.com/tripleyoung) to README.md

README.md

@@ -20,6 +20,14 @@ tags:
 
 # MiniMax-H3-Rung-Omega (`5.976 BPW`, `14.98 GiB` Joint-tANS / `16.22 GiB` Raw Base-243) + TheoremFlow-Ω (`8.92x` Speedup)
 
+<p align="left">
+  <a href="https://buymeacoffee.com/tripleyoung" target="_blank">
+    <img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" height="48" />
+  </a>
+</p>
+
+> ☕ **Support Open Quantization & Inference Acceleration Research**: If **`MiniMax-H3-Rung-Omega`** or **`TheoremFlow-Ω`** saves you GPU memory and generation time, consider supporting our independent AI research on [**Buy Me a Coffee (`buymeacoffee.com/tripleyoung`)**](https://buymeacoffee.com/tripleyoung)!
+
 **`yeowon/MiniMax-H3-Rung-Omega`** provides the **50-Block Pure `Rung Ω` Balanced Base-3 (`4-Trit`, Base-243 5-in-4-byte)** quantized checkpoint and the **`TheoremFlow-Ω` Mathematical Floor Inference Engine** for the **MiniMax-H3 FL2VA (First/Last-Frame-to-Video+Audio, 33.1B Total / 20.11B Active Parameters)** multimodal Diffusion Transformer.
 
 * **Zero Fallback (`200 / 200` Linear Layers in Pure `TensorCoreRungOmegaTernaryLayout`)**: Every single linear projection (`attn.qkv_proj`, `attn.out_proj`, `mlp.fc1`, `mlp.fc2`) across all 50 DiT blocks (`blocks.0` .. `blocks.49`) is quantized in the `Rung Ω` 4-Trit Balanced Base-3 lattice (`[-40, +40]` with `group_size=128` FP16 scales and `convrot_groupsize=256`), with **0 fallback NVFP4 layers**.
@@ -152,3 +160,20 @@ tf_state = install_theoremflow_omega_schedule(
    * **Floor 1 (Hardware Execution Roofline)**: Unpacks Base-243 weights once at load time into gauge-folded INT8 tensors (`-3.55 GiB` VRAM saved), pre-allocates a static contiguous CUDA workspace (eliminating 16,000+ `cudaMalloc`/`cudaFree` calls), fuses `SwiGLU + ConvRot64 + Rowwise INT8 Quantize` in `MLP.fc2`, and runs zero-transpose `NHD` `sageattn_qk_int8_pv_fp16_cuda`.
    * **Floor 2 & 3 (Bi-Time Intrinsic Flow & Boundary-Pinned Trunk Splitting)**: Evaluates exact boundary blocks and `FinalLayer` on the live Step-$k$ state while bridging the interior trunk via modality-decoupled Bi-Time Secant extrapolation along $(t_v, t_a)$.
    * **Floor 5 (Zero-Recompute Step-0 Constant Folding)**: Folds `PackedLayout`, `rope_rotation_table`, `TokenRefiner(condition_proj(text_states))`, and `video_patch_proj(cond_video_rows)` into Step-0 constants (`0.0 ms` overhead on Steps `1..19`).
+
+---
+
+## ☕ Support Our Research
+
+We release **`MiniMax-H3-Rung-Omega`** and **`TheoremFlow-Ω`** openly with zero gated access barriers so the community can run high-fidelity multimodal Video+Audio generation faster and in smaller VRAM footprints.
+
+If this model or inference engine helps your workflow or research, please consider buying us a coffee!
+
+<p align="left">
+  <a href="https://buymeacoffee.com/tripleyoung" target="_blank">
+    <img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" height="50" />
+  </a>
+</p>
+
+* **Buy Me a Coffee**: [https://buymeacoffee.com/tripleyoung](https://buymeacoffee.com/tripleyoung)
+