From 536f570e6692eec0656ef9689db7591ca1d0e0a7 Mon Sep 17 00:00:00 2001 From: Julian Huang Date: Thu, 27 Aug 2026 17:49:03 +0800 Subject: [PATCH] docs(cookbook): fix Qwen3.8 Flash Next H200 MTP verify with BF16 SSM state (#36611) --- docs/src/snippets/configs/Qwen/qwen3.8-flash-next.jsx | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/src/snippets/configs/Qwen/qwen3.8-flash-next.jsx b/docs/src/snippets/configs/Qwen/qwen3.8-flash-next.jsx index 92edf40f6..5a187d136 100644 --- a/docs/src/snippets/configs/Qwen/qwen3.8-flash-next.jsx +++ b/docs/src/snippets/configs/Qwen/qwen3.8-flash-next.jsx @@ -202,6 +202,7 @@ export const config = { "--chunked-prefill-size 8192", "--linear-attn-prefill-backend flashinfer", "--linear-attn-decode-backend flashinfer", + "--linear-attn-verify-backend triton", "--mamba-ssm-dtype bfloat16", "--speculative-algorithm NEXTN", "--speculative-num-steps 3", @@ -443,6 +444,7 @@ export const config = { "--chunked-prefill-size 8192", "--linear-attn-prefill-backend flashinfer", "--linear-attn-decode-backend flashinfer", + "--linear-attn-verify-backend triton", "--mamba-ssm-dtype bfloat16", "--speculative-algorithm NEXTN", "--speculative-num-steps 3",