[V1] V1 Enablement Oracle (#13726)
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com> Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com> Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com> Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com> Co-authored-by: Michael Goin <michael@neuralmagic.com>
This commit is contained in:
co-authored by
rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Nicolò Lucchesi
Tyler Michael Smith
Michael Goin
parent
8c0d15d5c5
commit
d4d93db2c5
@@ -74,7 +74,8 @@ def resolve_transformers_fallback(model_config: ModelConfig,
|
||||
if not is_transformers_impl_compatible(arch, custom_model_module):
|
||||
raise ValueError(
|
||||
f"{arch} has no vLLM implementation and the Transformers "
|
||||
"implementation is not compatible with vLLM.")
|
||||
"implementation is not compatible with vLLM. Try setting "
|
||||
"VLLM_USE_V1=0.")
|
||||
logger.warning(
|
||||
"%s has no vLLM implementation, falling back to Transformers "
|
||||
"implementation. Some features may not be supported and "
|
||||
|
||||
@@ -42,7 +42,7 @@ 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 .interfaces import SupportsPP, SupportsV0Only
|
||||
from .utils import (is_pp_missing_parameter,
|
||||
make_empty_intermediate_tensors_factory, make_layers,
|
||||
maybe_prefix)
|
||||
@@ -279,7 +279,7 @@ class BloomModel(nn.Module):
|
||||
return hidden_states
|
||||
|
||||
|
||||
class BloomForCausalLM(nn.Module, SupportsPP):
|
||||
class BloomForCausalLM(nn.Module, SupportsPP, SupportsV0Only):
|
||||
|
||||
def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
|
||||
super().__init__()
|
||||
|
||||
@@ -3,10 +3,11 @@
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.model_executor.models.llama import LlamaForCausalLM
|
||||
|
||||
from .interfaces import SupportsV0Only
|
||||
from .utils import PPMissingLayer
|
||||
|
||||
|
||||
class GlmForCausalLM(LlamaForCausalLM):
|
||||
class GlmForCausalLM(LlamaForCausalLM, SupportsV0Only):
|
||||
|
||||
def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
|
||||
super().__init__(vllm_config=vllm_config, prefix=prefix)
|
||||
|
||||
@@ -36,7 +36,7 @@ from vllm.sequence import IntermediateTensors
|
||||
from vllm.transformers_utils.configs.ultravox import UltravoxConfig
|
||||
|
||||
from .interfaces import (MultiModalEmbeddings, SupportsLoRA,
|
||||
SupportsMultiModal, SupportsPP)
|
||||
SupportsMultiModal, SupportsPP, SupportsV0Only)
|
||||
from .utils import (AutoWeightsLoader, WeightsMapper, flatten_bn,
|
||||
init_vllm_registered_model, maybe_prefix,
|
||||
merge_multimodal_embeddings,
|
||||
@@ -405,7 +405,8 @@ class ModifiedWhisperEncoder(WhisperEncoder):
|
||||
UltravoxMultiModalProcessor,
|
||||
info=UltravoxProcessingInfo,
|
||||
dummy_inputs=UltravoxDummyInputsBuilder)
|
||||
class UltravoxModel(nn.Module, SupportsMultiModal, SupportsPP, SupportsLoRA):
|
||||
class UltravoxModel(nn.Module, SupportsMultiModal, SupportsPP, SupportsLoRA,
|
||||
SupportsV0Only):
|
||||
|
||||
packed_modules_mapping = {
|
||||
"qkv_proj": ["q_proj", "k_proj", "v_proj"],
|
||||
|
||||
Reference in New Issue
Block a user