vllm.distributed.pp_transport.copy_engine
¶
PP transport on CUDA copy engines, synchronized on the GPU (one node).
Each rank shares one CUDA IPC buffer holding its flags and a receive region laid out like its persistent intermediate tensors. Per stage boundary, step N:
- sender: once the previous peer copy is done, pack the outputs into a local
send buffer; on a side stream, wait
empty >= N - 1, peer-copy into the receiver's region and writefull = N. - receiver: wait
full >= N, copy the region into the persistent tensors and writeempty = N.
Each flag lives on the GPU that waits on it and the peer writes it with stream memory ops, so neither SMs nor the CPU wait on the transfer. Metadata goes over the CPU group.
The waits omit CU_STREAM_WAIT_VALUE_FLUSH, which x86 hosts do not support. As in NCCL's zero-SM copy-engine path, this relies on NVLink delivering the peer copy before the flag write that follows it, so all PP GPUs must be NVLink peers.
The platform's flag ops and peer copy come from _CudaCopyEngines, or on ROCm
(gfx950) from rocm_sdma.SdmaCopyEngines, which uses HIP's stream memory ops
and SDMA engines.
Classes:
-
CopyEngineTransport– -
CopyEngineUnavailable–Copy engines are not usable. Raised on every rank alike.
CopyEngineTransport
¶
Bases: PPTransport
Methods:
-
__init__–Collective over the PP group. Raises
CopyEngineUnavailableon every -
recv–This step's tensors, as views of the persistent tensors. The wait
Source code in vllm/distributed/pp_transport/copy_engine.py
186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 | |
__init__(vllm_config, pp_group, persistent)
¶
Collective over the PP group. Raises CopyEngineUnavailable on every
rank alike, with nothing left allocated, if copy engines are not usable
on some rank.
Source code in vllm/distributed/pp_transport/copy_engine.py
187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 | |
recv(pp_group)
¶
This step's tensors, as views of the persistent tensors. The wait
for the previous stage and the copy are queued on the current stream
when .tensors is first read, so GPU work queued before then (input
preparation) overlaps the transfer, as with NCCL.
Source code in vllm/distributed/pp_transport/copy_engine.py
CopyEngineUnavailable
¶
Bases: RuntimeError
Copy engines are not usable. Raised on every rank alike.
_CudaCopyEngines
¶
CUDA's flag ops (stream memory ops) and, for a sender, its peer copy to the next stage (memcpys on copy engines).
Methods:
-
__init__–wordsandpeer_pciare for SDMA and unused here. -
copy–Queue on
streamthe copy of each key's firstrowsrows into the
Source code in vllm/distributed/pp_transport/copy_engine.py
__init__(send_buf, peer_recv_buf, peer_full, words, peer_pci)
¶
words and peer_pci are for SDMA and unused here.
Source code in vllm/distributed/pp_transport/copy_engine.py
copy(stream, layout, rows, seq)
¶
Queue on stream the copy of each key's first rows rows into the
peer's receive region, then the write of full = seq.
Source code in vllm/distributed/pp_transport/copy_engine.py
_Region
¶
Bases: NamedTuple
One tensor's region in a send or receive buffer.
Source code in vllm/distributed/pp_transport/copy_engine.py
_views(buf, layout, rows)
¶
The first rows[key] rows of each key's region of buf.