A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 8, 01:15 UTC
[V0 Deprecation] Remove unused MM placeholders in request output (#34944)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Feb 20, 2026 at 22:19 UTC
f9ac19204f0c4c3041d0afbe7d5eb4d63e73f15c
1 file changed
+1
-5
vllm/outputs.py
+1
-5
@@ -13,7 +13,6 @@ from typing_extensions import TypeVar
13
from vllm.logger import init_logger
14
from vllm.logprobs import PromptLogprobs, SampleLogprobs
15
from vllm.lora.request import LoRARequest
16
-from vllm.multimodal.inputs import MultiModalPlaceholderDict
16
from vllm.v1.metrics.stats import RequestStateStats
17
18
logger = init_logger(__name__)
@@ -121,7 +120,6 @@ class RequestOutput:
120
encoder_prompt_token_ids: list[int] | None = None,
121
num_cached_tokens: int | None = None,
122
*,
124
- multi_modal_placeholders: MultiModalPlaceholderDict | None = None,
123
kv_transfer_params: dict[str, Any] | None = None,
124
# Forward compatibility, code that uses args added in new release can
125
# still run with older versions of vLLM without breaking.
@@ -134,7 +132,6 @@ class RequestOutput:
132
self.request_id = request_id
133
self.prompt = prompt
134
self.prompt_token_ids = prompt_token_ids
137
- self.multi_modal_placeholders = multi_modal_placeholders or {}
135
self.prompt_logprobs = prompt_logprobs
136
self.outputs = outputs
137
self.finished = finished
@@ -187,8 +184,7 @@ class RequestOutput:
184
f"finished={self.finished}, "
185
f"metrics={self.metrics}, "
186
f"lora_request={self.lora_request}, "
190
- f"num_cached_tokens={self.num_cached_tokens}, "
191
- f"multi_modal_placeholders={self.multi_modal_placeholders})"
187
+ f"num_cached_tokens={self.num_cached_tokens})"
188
)
189
190