[docs] fix FastH3 installation instructions

README.md

@@ -3,7 +3,7 @@ license: other
 license_name: minimax-h3-community
 license_link: LICENSE
 base_model: MiniMaxAI/MiniMax-H3
-library_name: diffusers
+library_name: fastvideo
 pipeline_tag: text-to-video
 tags:
 - text-to-video
@@ -39,12 +39,20 @@ was trained with data-free DMD2 and VSA-H3 at 90% sparsity.
 
 ## Run with FastVideo
 
+Install [uv](https://docs.astral.sh/uv/getting-started/installation/), then use
+the CUDA 13 / Blackwell path below. It selects FastVideo's published CUDA
+kernel wheel instead of compiling the kernel locally. See the
+[installation guide](https://hao-ai-lab.github.io/FastVideo/getting_started/installation/)
+for other platforms.
+
 ```bash
 git clone https://github.com/hao-ai-lab/FastVideo.git
 cd FastVideo
-uv venv --python 3.12
+uv venv --python 3.12 --seed
 source .venv/bin/activate
-UV_TORCH_BACKEND=cu130 uv pip install -e ".[fasth3]"
+UV_TORCH_BACKEND=cu130 uv pip install \
+  --no-sources-package fastvideo-kernel \
+  -e ".[fasth3]"
 ```
 
 ```bash
@@ -55,9 +63,10 @@ python examples/inference/basic/basic_fasth3.py \
   --repeats 1
 ```
 
-The script uses FastVideo's optimized four-GPU defaults and the trained
-four-forward schedule. On systems without the Blackwell kernels, add
-`--vsa-kernel triton --no-fa4`; adjust `--num-gpus` for your setup.
+The tested defaults use four B200 GPUs and the trained four-forward schedule.
+On other multi-GPU CUDA systems, follow the installation guide and add
+`--no-replicated-dit --vsa-kernel triton --no-fa4`. The GPU count must divide
+H3's 56 attention heads.
 
 ## Scope