Update 2025-09-07 22:12:08

Author: zhaochen20

_sources/advanced_features/lora.ipynb

@@ -104,7 +104,7 @@ Overall, with these optimizations, we have achieved up to **7x** acceleration in
   <img src="https://lmsys.org/images/blog/sglang_v0_3/deepseek_mla.svg" alt="Multi-head Latent Attention for DeepSeek Series Models">
 </p>
 
-**Usage**: MLA optimization is enabled by default. For MLA models on Blackwell architecture (e.g., B200), the default backend is FlashInfer. To use the optimized TRTLLM MLA backend for decode operations, explicitly specify `--attention-backend trtllm_mla`. Note that TRTLLM MLA only optimizes decode operations - prefill operations (including multimodal inputs) will fall back to FlashInfer MLA.
+**Usage**: MLA optimization is enabled by default. For MLA models on Blackwell architecture (e.g., B200), the default backend is FlashInfer. To use the optimized TRTLLM MLA backend for prefill and decode operations, explicitly specify `--attention-backend trtllm_mla`.
 
 **Reference**: Check [Blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/#deepseek-multi-head-latent-attention-mla-throughput-optimizations) and [Slides](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/lmsys_1st_meetup_deepseek_mla.pdf) for more details.