minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[DeepSeek V4] Add W4A4 MegaMoE server flag (#35918)

Browse Source
This commit is contained in:
Baizhou Zhang
2026-08-21 18:44:18 -07:00
committed by GitHub
parent 0be2a209ac
commit 3b5909de0e
15 changed files with 147 additions and 87 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.claude/skills/cookbook-add-model/templates/config.jsx.tmpl
+3 -6
View File
@@ -211,7 +211,7 @@ sgl-eval run gsm8k \\
],
},
// MegaMoE quantization sub-select — shown only when backend === "megamoe".
// W4A4 adds the FP4-activations env vars; both strip the DeepEP dispatch env.
// W4A4 adds the FP4-activations server flag; 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"],
@@ -219,11 +219,8 @@ sgl-eval run gsm8k \\
{ 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",
] },
flags: ["--enable-w4a4-mxfp4-megamoe"],
env: ["SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK=8320"] },
],
},
ep: { label: "EP", values: [