[V1] Remove input cache client (#14864)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk> Signed-off-by: Roger Wang <ywang@roblox.com> Co-authored-by: Roger Wang <ywang@roblox.com>
This commit is contained in:
co-authored by
Roger Wang
parent
8d6cf89526
commit
b539222d4e
+23
-57
@@ -11,15 +11,15 @@ from vllm.inputs import (INPUT_REGISTRY, InputRegistry, ProcessorInputs,
|
||||
from vllm.inputs.parse import is_encoder_decoder_inputs
|
||||
from vllm.inputs.preprocess import InputPreprocessor
|
||||
from vllm.lora.request import LoRARequest
|
||||
from vllm.multimodal import (MULTIMODAL_REGISTRY, MultiModalHasher,
|
||||
MultiModalKwargs, MultiModalRegistry)
|
||||
from vllm.multimodal import (MULTIMODAL_REGISTRY, MultiModalKwargs,
|
||||
MultiModalRegistry)
|
||||
from vllm.multimodal.inputs import PlaceholderRange
|
||||
from vllm.multimodal.utils import merge_and_sort_multimodal_metadata
|
||||
from vllm.pooling_params import PoolingParams
|
||||
from vllm.prompt_adapter.request import PromptAdapterRequest
|
||||
from vllm.sampling_params import SamplingParams
|
||||
from vllm.transformers_utils.tokenizer_group import BaseTokenizerGroup
|
||||
from vllm.v1.engine import EngineCoreRequest
|
||||
from vllm.v1.engine.mm_input_cache import MMInputCacheClient
|
||||
from vllm.v1.structured_output.utils import validate_structured_output_request
|
||||
|
||||
|
||||
@@ -45,11 +45,6 @@ class Processor:
|
||||
self.input_preprocessor = InputPreprocessor(self.model_config,
|
||||
self.tokenizer,
|
||||
mm_registry)
|
||||
self.input_processor = input_registry.create_input_processor(
|
||||
self.model_config)
|
||||
|
||||
# Multi-modal (huggingface) input mapper
|
||||
self.mm_input_cache_client = MMInputCacheClient(self.model_config)
|
||||
|
||||
# Multi-modal hasher (for images)
|
||||
self.use_hash = (
|
||||
@@ -171,7 +166,7 @@ class Processor:
|
||||
# 2. For multimodal models with a merged preprocessor, preprocess
|
||||
# multimodal data and expand prompt token ids accordingly.
|
||||
# 3. Apply prompt adapter to prompt token ids if one exists.
|
||||
preprocessed_inputs = self.input_preprocessor.preprocess(
|
||||
processed_inputs: ProcessorInputs = self.input_preprocessor.preprocess(
|
||||
prompt,
|
||||
request_id=request_id,
|
||||
lora_request=lora_request,
|
||||
@@ -180,10 +175,6 @@ class Processor:
|
||||
)
|
||||
eos_token_id = self.input_preprocessor.get_eos_token_id(lora_request)
|
||||
|
||||
# Process prompt and prompt token ids.
|
||||
# Only applicable to multimodal models with legacy input processor.
|
||||
processed_inputs = self.input_processor(preprocessed_inputs)
|
||||
|
||||
self._validate_model_inputs(processed_inputs, lora_request)
|
||||
|
||||
if is_encoder_decoder_inputs(processed_inputs):
|
||||
@@ -212,36 +203,22 @@ class Processor:
|
||||
self.tokenizer.get_lora_tokenizer(lora_request))
|
||||
|
||||
# Multimodal related.
|
||||
# Compute MM hashes (if enabled)
|
||||
mm_hashes = None
|
||||
if self.use_hash:
|
||||
# Use mm_hashes from processed inputs if the model has merged
|
||||
# input processor.
|
||||
if decoder_inputs.multi_modal_hashes:
|
||||
mm_hashes = decoder_inputs.multi_modal_hashes
|
||||
# Fallback to using MultiModalHasher directly.
|
||||
else:
|
||||
mm_hashes = MultiModalHasher.hash_prompt_mm_data(prompt)
|
||||
sorted_mm_inputs: Optional[list[MultiModalKwargs]] = None
|
||||
sorted_mm_positions: Optional[list[PlaceholderRange]] = None
|
||||
sorted_mm_hashes: Optional[list[str]] = None
|
||||
if (decoder_mm_inputs := decoder_inputs.multi_modal_data):
|
||||
assert isinstance(decoder_mm_inputs, MultiModalKwargs)
|
||||
|
||||
# For merged preprocessor, mm_data is already mm_inputs
|
||||
precomputed_mm_inputs: Optional[list[MultiModalKwargs]] = None
|
||||
decoder_mm_data = decoder_inputs.multi_modal_data
|
||||
if isinstance(decoder_mm_data, MultiModalKwargs):
|
||||
# The output of merged multi-modal processor (`decoder_mm_data`)
|
||||
# The output of merged multi-modal processor (`decoder_mm_inputs`)
|
||||
# contains the kwargs for all items from all modalities.
|
||||
# This code separates them so that there is one set of kwargs
|
||||
# per item per modality.
|
||||
precomputed_mm_inputs = [
|
||||
individual_mm_inputs = [
|
||||
MultiModalKwargs.from_items([item])
|
||||
for modality in decoder_mm_data.modalities
|
||||
for item in decoder_mm_data.get_items(modality)
|
||||
for modality in decoder_mm_inputs.modalities
|
||||
for item in decoder_mm_inputs.get_items(modality)
|
||||
]
|
||||
|
||||
mm_positions = decoder_inputs.multi_modal_placeholders
|
||||
|
||||
# Last-mile processing of multimodal metadata and inputs.
|
||||
if mm_positions:
|
||||
|
||||
# Merge and flatten multimodal placeholders, hashes and inputs
|
||||
# from dictionaries to lists, and sort them by each item's position
|
||||
# in the input sequence.
|
||||
@@ -251,14 +228,13 @@ class Processor:
|
||||
sorted_mm_positions,
|
||||
sorted_mm_hashes,
|
||||
) = merge_and_sort_multimodal_metadata(
|
||||
mm_positions,
|
||||
mm_hashes,
|
||||
decoder_inputs.multi_modal_placeholders,
|
||||
decoder_inputs.multi_modal_hashes if self.use_hash else None,
|
||||
)
|
||||
|
||||
# NOTE: Sort multimodal inputs/kwargs ONLY IF there are multiple
|
||||
# modalities involved AND the model supports merged input processor.
|
||||
if len(sorted_modalities) > 1 and precomputed_mm_inputs:
|
||||
|
||||
# modalities involved.
|
||||
if len(sorted_modalities) > 1:
|
||||
modality_order_dict = {
|
||||
modality: order
|
||||
for order, modality in enumerate(sorted_modalities)
|
||||
@@ -266,26 +242,16 @@ class Processor:
|
||||
|
||||
# Sanity check to make sure each multimodal input has only one
|
||||
# modality key.
|
||||
for mm_input in precomputed_mm_inputs:
|
||||
for mm_input in individual_mm_inputs:
|
||||
assert len(mm_input.modalities) == 1
|
||||
|
||||
# Sort MultiModalKwags to match sorted_mm_positions
|
||||
precomputed_mm_inputs = sorted(
|
||||
precomputed_mm_inputs,
|
||||
# Sort MultiModalKwargs to match sorted_mm_positions
|
||||
sorted_mm_inputs = sorted(
|
||||
individual_mm_inputs,
|
||||
key=lambda mm_input: modality_order_dict[list(
|
||||
mm_input.modalities)[0]])
|
||||
|
||||
# Apply mm input cache update and legacy input mapper if one exists.
|
||||
sorted_mm_inputs = self.mm_input_cache_client.process_inputs(
|
||||
mm_data=decoder_mm_data,
|
||||
mm_hashes=sorted_mm_hashes,
|
||||
mm_processor_kwargs=decoder_inputs.mm_processor_kwargs,
|
||||
precomputed_mm_inputs=precomputed_mm_inputs,
|
||||
)
|
||||
else:
|
||||
sorted_mm_inputs = None
|
||||
sorted_mm_hashes = None
|
||||
sorted_mm_positions = None
|
||||
else:
|
||||
sorted_mm_inputs = individual_mm_inputs
|
||||
|
||||
return EngineCoreRequest(
|
||||
request_id=request_id,
|
||||
|
||||
Reference in New Issue
Block a user