docs(cookbook): fix Qwen3.8 Flash Next H200 MTP verify with BF16 SSM state (#36611)

This commit is contained in:
Julian Huang
2026-08-27 02:49:03 -07:00
committed by GitHub
parent ad911a5ec0
commit 536f570e66
@@ -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",