File size: 15,446 Bytes
ee3e701 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 |
#!/usr/bin/env python
# -*- encoding: utf-8 -*-
# adopted from https://github.com/hpcaitech/ColossalAI/blob/main/colossalai/context
import math
from abc import ABC, abstractmethod
from enum import Enum
import torch.distributed as dist
from internlm.utils.timeout import LLM_NCCL_TIMEOUT
# parallel modes
class ParallelMode(Enum):
"""This is an enumeration class containing all possible parallel modes."""
GLOBAL = "global"
# common parallel
DATA = "data"
# model parallel - containing tensor and pipeline parallel groups
# this is added to facilitate amp and grad clipping in hybrid parallel
MODEL = "model"
# pipeline parallel
PIPELINE = "pipe"
# containing all ranks in tensor parallel
TENSOR = "tensor"
# zero1 parallel
ZERO1 = "zero1"
# runntime network test
NETTEST = "nettest"
# dummy mode, only used during mode construction
DUMMY = "dummy"
class ProcessGroupInitializer(ABC):
"""An object, knowing the parallelism configuration, that initializes parallel groups.
Args:
rank (int): The rank of current process.
world_size (int): Size of whole communication world.
data_parallel_size (int): Size of data parallel.
pipeline_parallel_size (int): Size of pipeline parallel.
tensor_parallel_size (int): Size of tensor parallel.
zero1_parallel_size (int): Size of zero1 parallel.
"""
def __init__(
self,
rank: int,
world_size: int,
data_parallel_size: int,
pipeline_parallel_size: int,
tensor_parallel_size: int,
zero1_parallel_size: int,
nettest_parallel_size: int,
):
self.rank = rank
self.world_size = world_size
self.data_parallel_size = data_parallel_size
self.pipeline_parallel_size = pipeline_parallel_size
self.tensor_parallel_size = tensor_parallel_size
self.zero1_parallel_size = zero1_parallel_size
self.nettest_parallel_size = nettest_parallel_size
super().__init__()
@abstractmethod
def init_dist_group(self, use_cpu: bool = False):
pass
class Initializer_Data(ProcessGroupInitializer):
"""A ProcessGroupInitializer for data parallelism.
Args:
rank (int): The rank of current process.
world_size (int): Size of whole communication world.
data_parallel_size (int): Size of data parallel.
pipeline_parallel_size (int): Size of pipeline parallel.
tensor_parallel_size (int): Size of tensor parallel.
zero1_parallel_size (int): Size of zero1 parallel.
"""
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.rank_num_per_dp_group = self.world_size // self.data_parallel_size
assert self.world_size % self.data_parallel_size == 0
def init_dist_group(self, use_cpu: bool = False):
"""Initialize data parallel groups, and assign local_ranks and groups to each gpu.
Returns:
Tuple (local_rank, group_world_size, process_group, ranks_in_group, mode):
A Data parallelism's information tuple.
"""
local_rank = None
ranks_in_group = None
process_group = None
cpu_group = None
group_world_size = None
mode = ParallelMode.DATA
for i in range(self.rank_num_per_dp_group):
ranks = [i + j * self.rank_num_per_dp_group for j in range(self.data_parallel_size)]
group = dist.new_group(ranks, timeout=LLM_NCCL_TIMEOUT)
if use_cpu:
group_cpu = (
dist.new_group(ranks, backend="gloo", timeout=LLM_NCCL_TIMEOUT)
if dist.get_backend() != "gloo"
else group
)
else:
group_cpu = None
if self.rank in ranks:
local_rank = ranks.index(self.rank)
group_world_size = len(ranks)
process_group = group
cpu_group = group_cpu
ranks_in_group = ranks
return local_rank, group_world_size, process_group, cpu_group, ranks_in_group, mode
class Initializer_Model(ProcessGroupInitializer):
"""A ProcessGroupInitializer for model parallelism (model parallel group contains pipeline and tensor parallel
groups).
Args:
rank (int): The rank of current process.
world_size (int): Size of whole communication world.
data_parallel_size (int): Size of data parallel.
pipeline_parallel_size (int): Size of pipeline parallel.
tensor_parallel_size (int): Size of tensor parallel.
zero1_parallel_size (int): Size of zero1 parallel.
"""
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.rank_num_per_group = self.tensor_parallel_size * self.pipeline_parallel_size
self.num_group = self.world_size // self.rank_num_per_group
assert self.world_size % self.rank_num_per_group == 0
def init_dist_group(self, use_cpu: bool = False):
"""Initialize model parallel groups, and assign local_ranks and groups to each gpu.
Returns:
Tuple (local_rank, group_world_size, process_group, ranks_in_group, mode):
A Model parallelism's information tuple.
"""
local_rank = None
ranks_in_group = None
process_group = None
cpu_group = None
group_world_size = None
mode = ParallelMode.MODEL
for i in range(self.num_group):
ranks = [i * self.rank_num_per_group + j for j in range(self.rank_num_per_group)]
group = dist.new_group(ranks, timeout=LLM_NCCL_TIMEOUT)
if use_cpu:
group_cpu = (
dist.new_group(ranks, backend="gloo", timeout=LLM_NCCL_TIMEOUT)
if dist.get_backend() != "gloo"
else group
)
else:
group_cpu = None
if self.rank in ranks:
local_rank = ranks.index(self.rank)
group_world_size = len(ranks)
process_group = group
cpu_group = group_cpu
ranks_in_group = ranks
return local_rank, group_world_size, process_group, cpu_group, ranks_in_group, mode
class Initializer_Pipeline(ProcessGroupInitializer):
"""A ProcessGroupInitializer for pipeline parallelism.
Args:
rank (int): The rank of current process
world_size (int): Size of whole communication world
data_parallel_size (int): Size of data parallel
pipeline_parallel_size (int): Size of pipeline parallel
tensor_parallel_size (int): Size of tensor parallel
zero1_parallel_size (int): Size of zero1 parallel.
"""
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.rank_num_per_dp_group = self.world_size // self.data_parallel_size
self.pipeline_stage_size = self.rank_num_per_dp_group // self.pipeline_parallel_size
assert self.world_size % self.data_parallel_size == 0
assert self.rank_num_per_dp_group % self.pipeline_parallel_size == 0
def init_dist_group(self, use_cpu: bool = False):
"""Initialize pipeline parallel groups, and assign local_ranks and groups to each gpu.
Returns:
List[Tuple (local_rank, group_world_size, process_group, ranks_in_group, mode)]:
A Pipeline parallelism's information in list of tuples.
"""
local_rank = None
ranks_in_group = None
process_group = None
cpu_group = None
group_world_size = None
mode = ParallelMode.PIPELINE
for i in range(self.data_parallel_size):
for j in range(self.pipeline_stage_size):
ranks = list(
range(
i * self.rank_num_per_dp_group + j,
(i + 1) * self.rank_num_per_dp_group,
self.pipeline_stage_size,
)
)
pipe_group_size = len(ranks)
pipe_group = dist.new_group(ranks, timeout=LLM_NCCL_TIMEOUT)
if use_cpu:
group_cpu = (
dist.new_group(ranks, backend="gloo", timeout=LLM_NCCL_TIMEOUT)
if dist.get_backend() != "gloo"
else pipe_group
)
else:
group_cpu = None
if self.rank in ranks:
local_rank = ranks.index(self.rank)
group_world_size = pipe_group_size
process_group = pipe_group
cpu_group = group_cpu
ranks_in_group = ranks
return local_rank, group_world_size, process_group, cpu_group, ranks_in_group, mode
class Initializer_Tensor(ProcessGroupInitializer):
"""A ProcessGroupInitializer for tensor parallelism.
Args:
rank (int): The rank of current process.
world_size (int): Size of whole communication world.
data_parallel_size (int): Size of data parallel.
pipeline_parallel_size (int): Size of pipeline parallel.
tensor_parallel_size (int): Size of tensor parallel.
zero1_parallel_size (int): Size of zero1 parallel.
"""
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.num_tensor_parallel_group = self.world_size // self.tensor_parallel_size
assert self.world_size % self.tensor_parallel_size == 0
def init_dist_group(self, use_cpu: bool = False):
"""Initialize tensor parallel groups, and assign local_ranks and groups to each gpu.
Returns:
Tuple (local_rank, group_world_size, process_group, ranks_in_group, mode):
A Tensor parallelism's information tuple.
"""
local_rank = None
ranks_in_group = None
process_group = None
cpu_group = None
group_world_size = None
mode = ParallelMode.TENSOR
for i in range(self.num_tensor_parallel_group):
ranks = [i * self.tensor_parallel_size + j for j in range(self.tensor_parallel_size)]
group = dist.new_group(ranks, timeout=LLM_NCCL_TIMEOUT)
if use_cpu:
group_cpu = (
dist.new_group(ranks, backend="gloo", timeout=LLM_NCCL_TIMEOUT)
if dist.get_backend() != "gloo"
else group
)
else:
group_cpu = None
if self.rank in ranks:
local_rank = ranks.index(self.rank)
group_world_size = len(ranks)
process_group = group
cpu_group = group_cpu
ranks_in_group = ranks
return local_rank, group_world_size, process_group, cpu_group, ranks_in_group, mode
class Initializer_Zero1(ProcessGroupInitializer):
"""A ProcessGroupInitializer for zero-1 parallelism.
Args:
rank (int): The rank of current process.
world_size (int): Size of whole communication world.
data_parallel_size (int): Size of data parallel.
pipeline_parallel_size (int): Size of pipeline parallel.
tensor_parallel_size (int): Size of tensor parallel.
zero1_parallel_size (int): Size of zero-1 parallel.
"""
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.rank_num_per_dp_group = self.world_size // self.data_parallel_size
self.num_zero1_parallel_group = self.data_parallel_size // self.zero1_parallel_size
assert self.world_size % self.data_parallel_size == 0
assert self.world_size % self.zero1_parallel_size == 0
def init_dist_group(self, use_cpu: bool = False):
"""Initialize zero1 parallel groups, and assign local_ranks and groups to each gpu.
Returns:
Tuple (local_rank, group_world_size, process_group, ranks_in_group, mode):
A zero1 parallelism's information tuple.
"""
local_rank = None
ranks_in_group = None
process_group = None
cpu_group = None
group_world_size = None
mode = ParallelMode.ZERO1
for i in range(self.rank_num_per_dp_group):
for j in range(self.num_zero1_parallel_group):
ranks = [
i + (j * self.zero1_parallel_size + k) * self.rank_num_per_dp_group
for k in range(self.zero1_parallel_size)
]
group = dist.new_group(ranks, timeout=LLM_NCCL_TIMEOUT)
if use_cpu:
group_cpu = (
dist.new_group(ranks, backend="gloo", timeout=LLM_NCCL_TIMEOUT)
if dist.get_backend() != "gloo"
else group
)
else:
group_cpu = None
if self.rank in ranks:
local_rank = ranks.index(self.rank)
group_world_size = len(ranks)
process_group = group
cpu_group = group_cpu
ranks_in_group = ranks
return local_rank, group_world_size, process_group, cpu_group, ranks_in_group, mode
class Initializer_Nettest(ProcessGroupInitializer):
"""A ProcessGroupInitializer for network test, especailly for NCCL.
Args:
rank (int): The rank of current process.
world_size (int): Size of whole communication world.
nettest_parallel_size (int): Size of a network test group.
"""
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.num_nettest_group = math.ceil(self.world_size / self.nettest_parallel_size)
def init_dist_group(self, use_cpu: bool = False):
"""Initialize tensor parallel groups, and assign local_ranks and groups to each gpu.
Returns:
Tuple (local_rank, group_world_size, process_group, ranks_in_group, mode):
A Tensor parallelism's information tuple.
"""
local_rank = None
ranks_in_group = None
process_group = None
cpu_group = None
group_world_size = None
mode = ParallelMode.NETTEST
for i in range(self.num_nettest_group):
ranks = []
for j in range(self.nettest_parallel_size):
rank = i * self.nettest_parallel_size + j
if rank < self.world_size:
ranks.append(rank)
group = dist.new_group(ranks, timeout=LLM_NCCL_TIMEOUT)
if use_cpu:
group_cpu = (
dist.new_group(ranks, backend="gloo", timeout=LLM_NCCL_TIMEOUT)
if dist.get_backend() != "gloo"
else group
)
else:
group_cpu = None
if self.rank in ranks:
local_rank = ranks.index(self.rank)
group_world_size = len(ranks)
process_group = group
cpu_group = group_cpu
ranks_in_group = ranks
return local_rank, group_world_size, process_group, cpu_group, ranks_in_group, mode
|