docs(cookbook): DeepSeek-V4-Flash-0731 — drop chunked-prefill/autotune flags on B300 low-latency (#34044)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 5
parent
3dc91366ac
commit
86f373daff
@@ -620,7 +620,7 @@ sgl-eval run aime25 \\
|
|||||||
|
|
||||||
{
|
{
|
||||||
match: { hw: "b300", variant: "flash-official", quant: "fp4", strategy: "low-latency", nodes: "single" },
|
match: { hw: "b300", variant: "flash-official", quant: "fp4", strategy: "low-latency", nodes: "single" },
|
||||||
verified: false,
|
verified: true,
|
||||||
env: [],
|
env: [],
|
||||||
flags: [
|
flags: [
|
||||||
"--trust-remote-code",
|
"--trust-remote-code",
|
||||||
@@ -628,8 +628,6 @@ sgl-eval run aime25 \\
|
|||||||
"--tp 4",
|
"--tp 4",
|
||||||
"--moe-runner-backend flashinfer_mxfp4",
|
"--moe-runner-backend flashinfer_mxfp4",
|
||||||
"--speculative-algorithm DSPARK",
|
"--speculative-algorithm DSPARK",
|
||||||
"--chunked-prefill-size 4096",
|
|
||||||
"--disable-flashinfer-autotune",
|
|
||||||
"--swa-full-tokens-ratio 0.1",
|
"--swa-full-tokens-ratio 0.1",
|
||||||
"--host {{HOST_IP}}",
|
"--host {{HOST_IP}}",
|
||||||
"--port {{PORT}}",
|
"--port {{PORT}}",
|
||||||
|
|||||||
Reference in New Issue
Block a user