[Docs] Update MegaMoE handling and rerun benchmarks (#27726)
This commit is contained in:
@@ -178,10 +178,32 @@ sgl-eval run gsm8k \\
|
||||
options: [
|
||||
{ id: null, label: "Inherited" },
|
||||
{ id: "deepep", label: "DeepEP", flags: ["--moe-a2a-backend deepep"] },
|
||||
// KEEP the MegaMoE option + the megamoeQuant block below ONLY for Blackwell
|
||||
// MoE kernel-fusion models; DELETE both otherwise. requiresHw gates it to
|
||||
// Blackwell (the engine hides it elsewhere); add excludesStrategy: [...] too
|
||||
// for a strategy gate. Selecting MegaMoE reveals the Quantization sub-select.
|
||||
{ id: "megamoe", label: "MegaMoE", flags: ["--moe-a2a-backend megamoe"],
|
||||
requiresHw: ["b200", "b300", "gb200", "gb300"] },
|
||||
{ id: "flashinfer_mxfp4", label: "FlashInfer (MXFP4)", flags: ["--moe-runner-backend flashinfer_mxfp4"] },
|
||||
{ id: "marlin", label: "Marlin (W4A16)", flags: ["--moe-runner-backend marlin"] },
|
||||
],
|
||||
},
|
||||
// MegaMoE quantization sub-select — shown only when backend === "megamoe".
|
||||
// W4A4 adds the FP4-activations env vars; both strip the DeepEP dispatch env.
|
||||
// DELETE this block if there's no MegaMoE backend option above.
|
||||
megamoeQuant: {
|
||||
stripEnv: ["SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK"],
|
||||
options: [
|
||||
{ id: "w4a8", label: "W4A8",
|
||||
env: ["SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK=8320"] },
|
||||
{ id: "w4a4", label: "W4A4",
|
||||
env: [
|
||||
"SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK=8320",
|
||||
"SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS=1",
|
||||
"SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND=1",
|
||||
] },
|
||||
],
|
||||
},
|
||||
ep: { label: "EP", values: [
|
||||
null, 1, 2, 4, 8,
|
||||
{ value: 16, disable: { nodes: ["single"] },
|
||||
@@ -275,19 +297,6 @@ sgl-eval run gsm8k \\
|
||||
],
|
||||
defaultHostRatio: 10,
|
||||
},
|
||||
|
||||
// ----- Card: "MegaMoE" ----- KEEP only for Blackwell MoE kernel-fusion models.
|
||||
megamoe: {
|
||||
requiresHw: ["b200", "b300", "gb200", "gb300"],
|
||||
excludesStrategy: ["low-latency", "balanced"],
|
||||
stripEnv: ["SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK"],
|
||||
options: [
|
||||
{ id: "disabled", label: "Disabled" },
|
||||
{ id: "w4a8", label: "W4A8",
|
||||
flags: ["--moe-a2a-backend megamoe"],
|
||||
env: ["SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK=8320"] },
|
||||
],
|
||||
},
|
||||
},
|
||||
|
||||
// EXAMPLE cells — one per hardware family to show the shape. REPLACE each with
|
||||
|
||||
Reference in New Issue
Block a user