Update README.md

Author: jbschlosser

README.md

@@ -31,9 +31,10 @@ To install deps:
 pip install --pre torch==2.8.0.dev20250605+cu126 --index-url https://download.pytorch.org/whl/nightly/cu126
 pip install --pre torchao==0.12.0.dev20250609+cu126 --index-url https://download.pytorch.org/whl/nightly/cu126
 pip install diffusers==0.33.1
-MAX_JOBS=4 pip install flash-attn==3.0.0b1 --no-build-isolation
 ```
 
+To install flash attention v3, follow the instructions in https://github.com/Dao-AILab/flash-attention#flashattention-3-beta-release.
+
 For hardware, we used a 96GB 700W H100 GPU. Some of the optimizations applied (BFloat16, torch.compile, Combining q,k,v projections, dynamic float8 quantization) are available on CPU as well.
 
 ## Benchmarking