"--spec"
"miles_plugins.models.qwen3_next"
"get_qwen3_next_spec"
"--disable-bias-linear"
"--qk-layernorm"
"--group-query-attention"
"--num-attention-heads"
"16"
"--num-query-groups"
"2"
"--kv-channels"
"256"
"--num-layers"
"48"
"--hidden-size"
"2048"
"--ffn-hidden-size"
"5120"
"--normalization"
"RMSNorm"
"--apply-layernorm-1p"
"--position-embedding-type"
"rope"
"--norm-epsilon"
"1e-6"
"--rotary-percent"
"0.25"
"--swiglu"
"--untie-embeddings-and-output-weights"
"--vocab-size"
"151936"
"--rotary-base"
"10000000"
"--moe-ffn-hidden-size"
"512"
"--moe-shared-expert-intermediate-size"
"512"
"--moe-router-score-function"
"softmax"
"--moe-token-dispatcher-type"
"alltoall"
"--moe-router-topk"
"10"
"--moe-layer-freq"
"[1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]"
"--num-experts"
"512"
"--moe-grouped-gemm"
"--moe-token-drop-policy"
"probs"
"--moe-router-dtype"
"fp32"
"--moe-permute-fusion"
"--moe-aux-loss-coeff"
"0"
"--attention-output-gate"
"--moe-shared-expert-gate"
"--mtp-num-layers"
"1"
