vllm.models.minimax_m3.nvidia.specialized_decode.runtime.decode
¶
The specialized decode executor.
SpecializedDecode runs the decoder layers of MiniMaxM3Model for the
steps captured into FULL CUDA graphs of pure decode batches of up to
max_rows rows. Its model state builds it once the weights are loaded.
plan decides per forward whether it runs; the model's forward then passes
the returned DecodeStep to the backbone, which embeds the input as usual
and hands the layers to DecodeStep.run. Every other forward (prefill,
mixed, eager, PIECEWISE, larger batches) runs the stock layers, which the
executor leaves unchanged.
Per layer the executor runs the stock modules' weights through the stages of
stages.py:
- dense-attention layers (0-2): allreduce_norm.input -> front -> dense_decode -> o_proj -> allreduce_norm.post_attention -> dense_mlp;
- sparse-attention layers: allreduce_norm.input -> front -> index_score -> page_topk -> sparse_decode -> o_proj -> allreduce_norm.post_attention (+ router) -> moe (finalize deferred to the next input boundary when the stock MoE defers it and the next front does not fuse that boundary);
then allreduce_norm.final. A front that fuses_input replaces
allreduce_norm.input + front with run_fused; a MoE whose next front
polls_push pushes its output into that front's exchange. Each stage takes
the first of its implementations that runs over the deployment's cache dtypes,
supports the step's rows and is compatible with the other selected stages
(Stages.select); the last is always the stock one (stock.py).
The stages issue TP collectives, so every decision reads host state that all TP ranks share: the step's rows and the attention metadata's host fields.
Classes:
-
DecodeStep–The host-side choices of one captured decode step, by its rows.
-
SpecializedDecode–The decode executor over one backbone's local layers.
Functions:
-
captures_pure_decode–Whether the forward being captured into a CUDA graph is a FULL graph of
-
default_stages–The stage implementations of a deployment: the kernel stages
DecodeStep
¶
Bases: NamedTuple
The host-side choices of one captured decode step, by its rows.
Methods:
-
run–The backbone's output after its embedding.
Source code in vllm/models/minimax_m3/nvidia/specialized_decode/runtime/decode.py
run(hidden_states, positions)
¶
The backbone's output after its embedding.
SpecializedDecode
¶
The decode executor over one backbone's local layers.
Methods:
-
for_target–The executor of the target model's backbone.
-
plan–The step this forward runs, or None to run the stock layers: only
-
run–The decoder layers and the final norm of the step, on the embedding
Source code in vllm/models/minimax_m3/nvidia/specialized_decode/runtime/decode.py
115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 | |
for_target(backbone, config, lm_head)
classmethod
¶
The executor of the target model's backbone.
Source code in vllm/models/minimax_m3/nvidia/specialized_decode/runtime/decode.py
plan(positions, intermediate_tensors)
¶
The step this forward runs, or None to run the stock layers: only
FULL CUDA graph captures of pure decode steps of up to max_rows
rows run the executor.
Source code in vllm/models/minimax_m3/nvidia/specialized_decode/runtime/decode.py
run(step, x, positions)
¶
The decoder layers and the final norm of the step, on the embedding
x; returns what MiniMaxM3Model.forward returns.
Source code in vllm/models/minimax_m3/nvidia/specialized_decode/runtime/decode.py
211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 | |
captures_pure_decode(prefixes)
¶
Whether the forward being captured into a CUDA graph is a FULL graph of
a pure decode step: not a PIECEWISE capture (Model Runner V2 captures FULL
graphs with the forward context's mode NONE, and PIECEWISE ones, which
report capturing too, with PIECEWISE), and attention metadata without
prefills for every attention layer and index cache in prefixes.
Source code in vllm/models/minimax_m3/nvidia/specialized_decode/runtime/decode.py
default_stages(config, backbone=None)
¶
The stage implementations of a deployment: the kernel stages
(kernel_stages.py) that run over its cache dtypes, each ahead of the
stock stage. Without a backbone, the stock chain.