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

[V1] Remove input cache client (#14864)

Browse Source 
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:
Cyrus Leung
2025-03-17 14:42:06 +08:00
committed by GitHub
parent 8d6cf89526
commit b539222d4e
5 changed files with 48 additions and 201 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
vllm/v1/worker/gpu_model_runner.py
View File

@@ -29,7 +29,6 @@ from vllm.utils import (STR_DTYPE_TO_TORCH_DTYPE, DeviceMemoryProfiler,
is_pin_memory_available)
from vllm.v1.attention.backends.flash_attn import FlashAttentionMetadata
from vllm.v1.core.encoder_cache_manager import compute_encoder_budget
from vllm.v1.engine.mm_input_cache import MMInputCacheClient
from vllm.v1.kv_cache_interface import (FullAttentionSpec, KVCacheConfig,
KVCacheSpec)
from vllm.v1.outputs import (EMPTY_MODEL_RUNNER_OUTPUT, LogprobsTensors,
@@ -133,14 +132,6 @@ class GPUModelRunner(LoRAModelRunnerMixin):
self.mm_registry = MULTIMODAL_REGISTRY
self.uses_mrope = model_config.uses_mrope
if self.is_multimodal_model:
# NOTE: Initialized client is only used for processing dummy
# multimodal data into multimodal kwargs for GPU memory profiling.
# Only applicable to multimodal models with legacy input mapper.
self.mm_input_mapper_profiling = MMInputCacheClient(
self.model_config)
self.mm_input_mapper_profiling.use_cache = False
encoder_compute_budget, encoder_cache_size = compute_encoder_budget(
model_config=model_config,
scheduler_config=scheduler_config,
@@ -1376,32 +1367,18 @@ class GPUModelRunner(LoRAModelRunnerMixin):
mm_registry=self.mm_registry,
)
dummy_mm_data = dummy_request_data.multi_modal_data
if not isinstance(dummy_mm_data, MultiModalKwargs):
# TODO: Delete this check once input mapper is fully removed.
raise RuntimeError(
"Legacy input mapper is not supported in V1")
# Dummy data definition in V0 may contain multiple multimodal items
# Dummy data definition may contain multiple multimodal items
# (e.g, multiple images) for a single request, therefore here we
# always replicate first item by max_num_mm_items times since in V1
# they are scheduled to be processed separately.
# Case when models have a merged processor, their dummy data is
# already batched `MultiModalKwargs`, therefore we take the first
# `MultiModalKwargsItem` from the desired modality to profile on.
if isinstance(dummy_mm_data, MultiModalKwargs):
dummy_mm_item = dummy_mm_data.get_item(
modality=dummy_data_modality, item_index=0)
dummy_mm_kwargs = MultiModalKwargs.from_items([dummy_mm_item])
# Case when models have dummy data explicitly defined as
# `MultiModalDataDict`, so they need to be processed through input
# mapper.
# TODO (ywang96): deprecate this path once merged processor is
# supported on all models.
else:
mm_kwargs_list = self.mm_input_mapper_profiling.process_inputs(
mm_data=dummy_mm_data,
mm_hashes=None,
mm_processor_kwargs=None,
precomputed_mm_inputs=None)
dummy_mm_kwargs = mm_kwargs_list[0]
dummy_mm_item = dummy_mm_data.get_item(
modality=dummy_data_modality, item_index=0)
dummy_mm_kwargs = MultiModalKwargs.from_items([dummy_mm_item])
batched_dummy_mm_inputs = MultiModalKwargs.batch(
[dummy_mm_kwargs] * max_num_mm_items)