docs(cookbook): fix Qwen3.8 Flash Next H200 MTP verify with BF16 SSM state (#36611)
This commit is contained in:
@@ -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",
|
||||
|
||||
Reference in New Issue
Block a user