Update README.md

README.md

@@ -134,6 +134,7 @@ input_ids = tokenizer("The capital of France is", return_tensors="pt").input_ids
 output = model.generate(input_ids.to(model.device), max_new_tokens=32)
 print(tokenizer.decode(output[0]))
 ```
+Note that `quartet_2_impl="quartet2"` only supports inputs with `(micro_batch_size * seq_length) % 128 == 0`.
 
 ### Running Evaluations