[Models] Add remaining model PP support (#7168)
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai> Signed-off-by: Murali Andoorveedu <muralidhar.andoorveedu@centml.ai> Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
co-authored by
DarkLight1337
parent
303d44790a
commit
0f6d7a9a34
@@ -21,7 +21,7 @@
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
"""Inference-only Mixtral model."""
|
||||
from typing import Iterable, List, Optional, Tuple
|
||||
from typing import Iterable, List, Optional, Tuple, Union
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
@@ -31,7 +31,7 @@ from transformers import MixtralConfig
|
||||
|
||||
from vllm.attention import Attention, AttentionMetadata
|
||||
from vllm.config import CacheConfig
|
||||
from vllm.distributed import (get_tensor_model_parallel_rank,
|
||||
from vllm.distributed import (get_pp_group, get_tensor_model_parallel_rank,
|
||||
get_tensor_model_parallel_world_size,
|
||||
tensor_model_parallel_all_reduce)
|
||||
from vllm.model_executor.layers.layernorm import RMSNorm
|
||||
@@ -39,8 +39,7 @@ from vllm.model_executor.layers.linear import (QKVParallelLinear,
|
||||
ReplicatedLinear,
|
||||
RowParallelLinear)
|
||||
from vllm.model_executor.layers.logits_processor import LogitsProcessor
|
||||
from vllm.model_executor.layers.quantization.base_config import (
|
||||
QuantizationConfig)
|
||||
from vllm.model_executor.layers.quantization import QuantizationConfig
|
||||
from vllm.model_executor.layers.rotary_embedding import get_rope
|
||||
from vllm.model_executor.layers.sampler import Sampler, SamplerOutput
|
||||
from vllm.model_executor.layers.vocab_parallel_embedding import (
|
||||
@@ -49,6 +48,10 @@ from vllm.model_executor.model_loader.weight_utils import default_weight_loader
|
||||
from vllm.model_executor.sampling_metadata import SamplingMetadata
|
||||
from vllm.sequence import IntermediateTensors
|
||||
|
||||
from .interfaces import SupportsPP
|
||||
from .utils import (is_pp_missing_parameter,
|
||||
make_empty_intermediate_tensors_factory, make_layers)
|
||||
|
||||
|
||||
class MixtralMLP(nn.Module):
|
||||
|
||||
@@ -296,6 +299,7 @@ class MixtralModel(nn.Module):
|
||||
config: MixtralConfig,
|
||||
cache_config: Optional[CacheConfig] = None,
|
||||
quant_config: Optional[QuantizationConfig] = None,
|
||||
prefix: str = "",
|
||||
) -> None:
|
||||
super().__init__()
|
||||
self.padding_idx = config.pad_token_id
|
||||
@@ -305,13 +309,15 @@ class MixtralModel(nn.Module):
|
||||
config.vocab_size,
|
||||
config.hidden_size,
|
||||
)
|
||||
self.layers = nn.ModuleList([
|
||||
MixtralDecoderLayer(config,
|
||||
cache_config,
|
||||
quant_config=quant_config)
|
||||
for _ in range(config.num_hidden_layers)
|
||||
])
|
||||
self.start_layer, self.end_layer, self.layers = make_layers(
|
||||
config.num_hidden_layers,
|
||||
lambda prefix: MixtralDecoderLayer(
|
||||
config, cache_config, quant_config=quant_config),
|
||||
prefix=f"{prefix}.layers")
|
||||
self.norm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
|
||||
self.make_empty_intermediate_tensors = (
|
||||
make_empty_intermediate_tensors_factory(
|
||||
["hidden_states", "residual"], config.hidden_size))
|
||||
|
||||
def forward(
|
||||
self,
|
||||
@@ -319,19 +325,30 @@ class MixtralModel(nn.Module):
|
||||
positions: torch.Tensor,
|
||||
kv_caches: List[torch.Tensor],
|
||||
attn_metadata: AttentionMetadata,
|
||||
) -> torch.Tensor:
|
||||
hidden_states = self.embed_tokens(input_ids)
|
||||
residual = None
|
||||
for i in range(len(self.layers)):
|
||||
intermediate_tensors: Optional[IntermediateTensors],
|
||||
) -> Union[torch.Tensor, IntermediateTensors]:
|
||||
if get_pp_group().is_first_rank:
|
||||
hidden_states = self.embed_tokens(input_ids)
|
||||
residual = None
|
||||
else:
|
||||
assert intermediate_tensors is not None
|
||||
hidden_states = intermediate_tensors["hidden_states"]
|
||||
residual = intermediate_tensors["residual"]
|
||||
for i in range(self.start_layer, self.end_layer):
|
||||
layer = self.layers[i]
|
||||
hidden_states, residual = layer(positions, hidden_states,
|
||||
kv_caches[i], attn_metadata,
|
||||
residual)
|
||||
kv_caches[i - self.start_layer],
|
||||
attn_metadata, residual)
|
||||
if not get_pp_group().is_last_rank:
|
||||
return IntermediateTensors({
|
||||
"hidden_states": hidden_states,
|
||||
"residual": residual
|
||||
})
|
||||
hidden_states, _ = self.norm(hidden_states, residual)
|
||||
return hidden_states
|
||||
|
||||
|
||||
class MixtralForCausalLM(nn.Module):
|
||||
class MixtralForCausalLM(nn.Module, SupportsPP):
|
||||
fall_back_to_pt_during_load = False
|
||||
|
||||
def __init__(
|
||||
@@ -351,6 +368,8 @@ class MixtralForCausalLM(nn.Module):
|
||||
self.lm_head.weight = self.model.embed_tokens.weight
|
||||
self.logits_processor = LogitsProcessor(config.vocab_size)
|
||||
self.sampler = Sampler()
|
||||
self.make_empty_intermediate_tensors = (
|
||||
self.model.make_empty_intermediate_tensors)
|
||||
|
||||
def forward(
|
||||
self,
|
||||
@@ -359,9 +378,9 @@ class MixtralForCausalLM(nn.Module):
|
||||
kv_caches: List[torch.Tensor],
|
||||
attn_metadata: AttentionMetadata,
|
||||
intermediate_tensors: Optional[IntermediateTensors] = None,
|
||||
) -> torch.Tensor:
|
||||
) -> Union[torch.Tensor, IntermediateTensors]:
|
||||
hidden_states = self.model(input_ids, positions, kv_caches,
|
||||
attn_metadata)
|
||||
attn_metadata, intermediate_tensors)
|
||||
return hidden_states
|
||||
|
||||
def compute_logits(
|
||||
@@ -400,6 +419,8 @@ class MixtralForCausalLM(nn.Module):
|
||||
# Skip loading extra bias for GPTQ models.
|
||||
if name.endswith(".bias") and name not in params_dict:
|
||||
continue
|
||||
if is_pp_missing_parameter(name, self):
|
||||
continue
|
||||
param = params_dict[name]
|
||||
weight_loader = param.weight_loader
|
||||
weight_loader(param, loaded_weight, shard_id)
|
||||
@@ -412,6 +433,8 @@ class MixtralForCausalLM(nn.Module):
|
||||
if ("block_sparse_moe.experts." in name
|
||||
and name not in params_dict):
|
||||
continue
|
||||
if is_pp_missing_parameter(name, self):
|
||||
continue
|
||||
param = params_dict[name]
|
||||
weight_loader = getattr(param, "weight_loader",
|
||||
default_weight_loader)
|
||||
|
||||
Reference in New Issue
Block a user