fix

Signed-off-by: Amog Kamsetty <amogkamsetty@gmail.com>

Author: amogkam

vllm/v1/core/sched/scheduler.py

@@ -823,16 +823,11 @@ def update_from_output(
                         new_prompt_logprobs_tensors=prompt_logprobs_tensors,
                         stop_reason=request.stop_reason,
                         events=request.take_events(),
-<<<<<<< HEAD
                         new_additional_head_outputs=
                         additional_head_outputs_per_request,
-                    ))
-=======
                         kv_transfer_params=kv_transfer_params,
                         num_cached_tokens=request.num_cached_tokens,
                     ))
-
->>>>>>> b6553be1bc75f046b00046a4ad7576364d03c835
             else:
                 # Invariant: EngineCore returns no partial prefill outputs.
                 assert not prompt_logprobs_tensors

vllm/v1/engine/async_llm.py

@@ -21,12 +21,9 @@
 from vllm.pooling_params import PoolingParams
 from vllm.prompt_adapter.request import PromptAdapterRequest
 from vllm.sampling_params import SamplingParams
-<<<<<<< HEAD
 from vllm.streaming_params import StreamingParams
-=======
 from vllm.transformers_utils.config import (
     maybe_register_config_serialize_by_value)
->>>>>>> b6553be1bc75f046b00046a4ad7576364d03c835
 from vllm.transformers_utils.tokenizer import AnyTokenizer
 from vllm.transformers_utils.tokenizer_group import init_tokenizer_from_configs
 from vllm.usage.usage_lib import UsageContext

vllm/v1/worker/gpu_model_runner.py

@@ -1538,12 +1538,9 @@ def execute_model(
             spec_token_ids=spec_token_ids,
             logprobs=logprobs_lists,
             prompt_logprobs_dict=prompt_logprobs_dict,
-<<<<<<< HEAD
             additional_head_outputs=additional_head_outputs,
-=======
             finished_sending=finished_sending,
             finished_recving=finished_recving,
->>>>>>> b6553be1bc75f046b00046a4ad7576364d03c835
         )
 
     def kv_connector_no_forward(