Update README.md

README.md

@@ -96,7 +96,7 @@ Laguna XS.2 is supported in vLLM, SGLang, and Transformers, and TRT-LLM thanks t
 
 #### vLLM
 
-The full vLLM recipe is on the main [Laguna XS.2 model card](https://huggingface.co/poolside/Laguna-XS.2) and on the [vLLM recipes page](https://recipes.vllm.ai/poolside/Laguna-XS.2). Quantization is detected automatically from `quantization_config` in this checkpoint, so the same command works with `poolside/Laguna-XS.2-FP8` substituted for the model ID. No extra flags required.
+The full vLLM recipe is on the main [Laguna XS.2 model card](https://huggingface.co/poolside/Laguna-XS.2) and on the [vLLM recipes page](https://recipes.vllm.ai/poolside/Laguna-XS.2). Quantization is detected automatically from `quantization_config` in this checkpoint, so the same command works with `poolside/Laguna-XS.2-FP8` substituted for the model ID. Set `VLLM_BLOCKSCALE_FP8_GEMM_FLASHINFER=0` when serving with vLLM.
 
 > [!NOTE]
 > The FP8-quantized KV cache requires vLLM >= 0.22.0. Earlier versions produce scrambled output on non-Hopper GPUs because of a per-layer attention-head count bug, fixed in [vllm#42650](https://github.com/vllm-project/vllm/pull/42650). On older vLLM, disable the FP8 KV cache by adding `--kv-cache-dtype-skip-layers $(seq 0 39)`.