biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Models] Add remaining model PP support (#7168)

Browse Source 
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:
Murali Andoorveedu
2024-10-03 19:56:58 -07:00
committed by GitHub
parent 303d44790a
commit 0f6d7a9a34
69 changed files with 2585 additions and 1344 deletions
Download Patch File Download Diff File Expand all files Collapse all files

65
vllm/model_executor/models/baichuan.py
View File

@@ -19,7 +19,7 @@
# limitations under the License.
"""Inference-only BaiChuan model compatible with HuggingFace weights."""
import math
from typing import Iterable, List, Optional, Tuple
from typing import Iterable, List, Optional, Tuple, Union
import torch
from torch import nn
@@ -27,7 +27,7 @@ from transformers import PretrainedConfig
from vllm.attention import Attention, AttentionMetadata
from vllm.config import CacheConfig, LoRAConfig
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)
from vllm.model_executor.layers.activation import SiluAndMul
from vllm.model_executor.layers.layernorm import RMSNorm
@@ -35,8 +35,7 @@ from vllm.model_executor.layers.linear import (MergedColumnParallelLinear,
QKVParallelLinear,
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 (
@@ -45,7 +44,9 @@ 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 SupportsLoRA
from .interfaces import SupportsLoRA, SupportsPP
from .utils import (is_pp_missing_parameter,
make_empty_intermediate_tensors_factory, make_layers)
def _get_alibi_slopes(total_num_heads: int) -> torch.Tensor:
@@ -255,7 +256,8 @@ class BaiChuanModel(nn.Module):
config: PretrainedConfig,
position_embedding: str,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None):
quant_config: Optional[QuantizationConfig] = None,
prefix: str = ""):
super().__init__()
self.config = config
self.padding_idx = config.pad_token_id
@@ -265,12 +267,16 @@ class BaiChuanModel(nn.Module):
config.vocab_size,
config.hidden_size,
)
self.layers = nn.ModuleList([
BaiChuanDecoderLayer(config, position_embedding, cache_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: BaiChuanDecoderLayer(config, position_embedding,
cache_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,
@@ -278,23 +284,34 @@ class BaiChuanModel(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],
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 BaiChuanBaseForCausalLM(nn.Module, SupportsLoRA):
class BaiChuanBaseForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
packed_modules_mapping = {
"W_pack": ["W_pack"],
"gate_up_proj": [
@@ -335,6 +352,8 @@ class BaiChuanBaseForCausalLM(nn.Module, SupportsLoRA):
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,
@@ -343,9 +362,9 @@ class BaiChuanBaseForCausalLM(nn.Module, SupportsLoRA):
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(
@@ -394,6 +413,8 @@ class BaiChuanBaseForCausalLM(nn.Module, SupportsLoRA):
# 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)
@@ -402,6 +423,8 @@ class BaiChuanBaseForCausalLM(nn.Module, SupportsLoRA):
# 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 = getattr(param, "weight_loader",
default_weight_loader)
@@ -413,7 +436,7 @@ class BaichuanForCausalLM(BaiChuanBaseForCausalLM):
def __init__(
self,
config,
config: PretrainedConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
lora_config: Optional[LoRAConfig] = None,
@@ -431,7 +454,7 @@ class BaiChuanForCausalLM(BaiChuanBaseForCausalLM):
def __init__(
self,
config,
config: PretrainedConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
lora_config: Optional[LoRAConfig] = None,