RuntimeError: Engine core initialization failed.
#8
by InformaticsSolutions - opened
- vllm version 0.25.1.dev833+g92c104112 installed as per the instructions
- vllm started exactly as pe the instructions, no other flags
- GPUs: 2x RTX 6000 Pro Blackwell
In the console:
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] WorkerProc failed to start.
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] Traceback (most recent call last):
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/v1/executor/multiproc_executor.py", line 879, in worker_main
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] worker = WorkerProc(*args, **kwargs)
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/tracing/otel.py", line 178, in sync_wrapper
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] return func(*args, **kwargs)
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/v1/executor/multiproc_executor.py", line 648, in __init__
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.worker.load_model()
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~~~^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/v1/worker/gpu_worker.py", line 442, in load_model
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.model_runner.load_model(load_dummy_weights=load_dummy_weights)
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/tracing/otel.py", line 178, in sync_wrapper
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] return func(*args, **kwargs)
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/v1/worker/gpu_model_runner.py", line 5324, in load_model
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.model = model_loader.load_model(
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~~~~^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] vllm_config=self.vllm_config, model_config=self.model_config
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/tracing/otel.py", line 178, in sync_wrapper
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] return func(*args, **kwargs)
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/model_loader/base_loader.py", line 55, in load_model
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] model = initialize_model(
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] vllm_config=vllm_config,
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] model_config=model_config,
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] prefix=prefix,
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/tracing/otel.py", line 178, in sync_wrapper
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] return func(*args, **kwargs)
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/model_loader/utils.py", line 62, in initialize_model
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] model = model_class(vllm_config=vllm_config, prefix=prefix)
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/models/bailing_moe_v3.py", line 1158, in __init__
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.model = BailingMoeV3Model(
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] vllm_config=vllm_config, prefix=maybe_prefix(prefix, "model")
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/compilation/decorators.py", line 383, in __init__
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] old_init(self, *args, **kwargs)
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/models/bailing_moe_v3.py", line 1090, in __init__
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.start_layer, self.end_layer, self.layers = make_layers(
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.num_layers, layer_fn, prefix=f"{prefix}.layers"
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/models/utils.py", line 824, in make_layers
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] + get_offloader().wrap_modules(
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] layer_fn(prefix=f"{prefix}.{idx}") for idx in range(start_layer, end_layer)
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/offloader/base.py", line 104, in wrap_modules
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] return list(modules_generator)
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/models/utils.py", line 825, in <genexpr>
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] layer_fn(prefix=f"{prefix}.{idx}") for idx in range(start_layer, end_layer)
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/models/bailing_moe_v3.py", line 1080, in layer_fn
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] return BailingMoeV3DecoderLayer(
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] config=config,
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ...<5 lines>...
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] num_speculative_tokens=num_speculative_tokens,
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/models/bailing_moe_v3.py", line 991, in __init__
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.self_attn = BailingMoeV3MLAAttention(
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~~~~~^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] config,
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ...<3 lines>...
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] cache_config=cache_config,
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/models/bailing_moe_v3.py", line 321, in __init__
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ColumnParallelLinear(
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.hidden_size,
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ...<3 lines>...
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] prefix=f"{prefix}.g_proj",
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/layers/linear.py", line 504, in __init__
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.quant_method.create_weights(
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] layer=self,
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ...<9 lines>...
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ),
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/layers/quantization/fp8.py", line 333, in create_weights
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] validate_fp8_block_shape(
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~~~~~^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] layer,
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ...<4 lines>...
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.weight_block_size,
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/layers/quantization/utils/fp8_utils.py", line 1236, in validate_fp8_block_shape
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] raise ValueError(
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ...<3 lines>...
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP1_EP1 pid=1235611) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ValueError: Weight output_partition_size = 16 is not divisible by weight quantization block_n = 128.
(EngineCore pid=1235548) INFO 08-19 12:28:29 [multiproc_executor.py:440] [shutdown] Executor: waiting for worker exit count=2
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] WorkerProc failed to start.
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] Traceback (most recent call last):
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/v1/executor/multiproc_executor.py", line 879, in worker_main
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] worker = WorkerProc(*args, **kwargs)
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/tracing/otel.py", line 178, in sync_wrapper
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] return func(*args, **kwargs)
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/v1/executor/multiproc_executor.py", line 648, in __init__
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.worker.load_model()
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~~~^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/v1/worker/gpu_worker.py", line 442, in load_model
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.model_runner.load_model(load_dummy_weights=load_dummy_weights)
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/tracing/otel.py", line 178, in sync_wrapper
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] return func(*args, **kwargs)
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/v1/worker/gpu_model_runner.py", line 5324, in load_model
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.model = model_loader.load_model(
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~~~~^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] vllm_config=self.vllm_config, model_config=self.model_config
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/tracing/otel.py", line 178, in sync_wrapper
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] return func(*args, **kwargs)
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/model_loader/base_loader.py", line 55, in load_model
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] model = initialize_model(
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] vllm_config=vllm_config,
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] model_config=model_config,
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] prefix=prefix,
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/tracing/otel.py", line 178, in sync_wrapper
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] return func(*args, **kwargs)
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/model_loader/utils.py", line 62, in initialize_model
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] model = model_class(vllm_config=vllm_config, prefix=prefix)
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/models/bailing_moe_v3.py", line 1158, in __init__
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.model = BailingMoeV3Model(
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] vllm_config=vllm_config, prefix=maybe_prefix(prefix, "model")
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/compilation/decorators.py", line 383, in __init__
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] old_init(self, *args, **kwargs)
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/models/bailing_moe_v3.py", line 1090, in __init__
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.start_layer, self.end_layer, self.layers = make_layers(
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.num_layers, layer_fn, prefix=f"{prefix}.layers"
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/models/utils.py", line 824, in make_layers
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] + get_offloader().wrap_modules(
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] layer_fn(prefix=f"{prefix}.{idx}") for idx in range(start_layer, end_layer)
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/offloader/base.py", line 104, in wrap_modules
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] return list(modules_generator)
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/models/utils.py", line 825, in <genexpr>
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] layer_fn(prefix=f"{prefix}.{idx}") for idx in range(start_layer, end_layer)
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/models/bailing_moe_v3.py", line 1080, in layer_fn
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] return BailingMoeV3DecoderLayer(
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] config=config,
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ...<5 lines>...
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] num_speculative_tokens=num_speculative_tokens,
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/models/bailing_moe_v3.py", line 991, in __init__
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.self_attn = BailingMoeV3MLAAttention(
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~~~~~^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] config,
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ...<3 lines>...
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] cache_config=cache_config,
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/models/bailing_moe_v3.py", line 321, in __init__
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ColumnParallelLinear(
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.hidden_size,
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ...<3 lines>...
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] prefix=f"{prefix}.g_proj",
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/layers/linear.py", line 504, in __init__
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.quant_method.create_weights(
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] layer=self,
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ...<9 lines>...
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ),
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/layers/quantization/fp8.py", line 333, in create_weights
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] validate_fp8_block_shape(
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ~~~~~~~~~~~~~~~~~~~~~~~~^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] layer,
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ...<4 lines>...
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] self.weight_block_size,
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ^
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] File "/home/user1/vllm-ling-v3/vllm/model_executor/layers/quantization/utils/fp8_utils.py", line 1236, in validate_fp8_block_shape
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] raise ValueError(
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ...<3 lines>...
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] )
(Worker_TP0_EP0 pid=1235610) ERROR 08-19 12:28:29 [multiproc_executor.py:912] ValueError: Weight output_partition_size = 16 is not divisible by weight quantization block_n = 128.
[rank0]:[W819 12:28:30.341804515 ProcessGroupNCCL.cpp:1624] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
(EngineCore pid=1235548) INFO 08-19 12:28:31 [multiproc_executor.py:447] [shutdown] Executor: all workers exited gracefully
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] EngineCore failed to start.
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] Traceback (most recent call last):
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] File "/home/user1/vllm-ling-v3/vllm/v1/engine/core.py", line 1318, in run_engine_core
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] engine_core = EngineCoreProc(*args, engine_index=dp_rank, **kwargs)
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] File "/home/user1/vllm-ling-v3/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] return func(*args, **kwargs)
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] File "/home/user1/vllm-ling-v3/vllm/v1/engine/core.py", line 1074, in __init__
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] super().__init__(
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] ~~~~~~~~~~~~~~~~^
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] vllm_config,
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] ^^^^^^^^^^^^
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] ...<3 lines>...
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] internal_dp_balancing,
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] ^^^^^^^^^^^^^^^^^^^^^^
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] )
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] ^
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] File "/home/user1/vllm-ling-v3/vllm/v1/engine/core.py", line 132, in __init__
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] self.model_executor = executor_class(vllm_config)
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] ~~~~~~~~~~~~~~^^^^^^^^^^^^^
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] File "/home/user1/vllm-ling-v3/vllm/v1/executor/multiproc_executor.py", line 108, in __init__
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] super().__init__(vllm_config)
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] File "/home/user1/vllm-ling-v3/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] return func(*args, **kwargs)
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] File "/home/user1/vllm-ling-v3/vllm/v1/executor/abstract.py", line 109, in __init__
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] self._init_executor()
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] ~~~~~~~~~~~~~~~~~~~^^
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] File "/home/user1/vllm-ling-v3/vllm/v1/executor/multiproc_executor.py", line 201, in _init_executor
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] self.workers = WorkerProc.wait_for_ready(unready_workers)
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] ~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] File "/home/user1/vllm-ling-v3/vllm/v1/executor/multiproc_executor.py", line 776, in wait_for_ready
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] raise e from None
(EngineCore pid=1235548) ERROR 08-19 12:28:31 [core.py:1349] Exception: WorkerProc initialization failed due to an exception in a background process. See stack trace for root cause.
(EngineCore pid=1235548) Process EngineCore:
(EngineCore pid=1235548) Traceback (most recent call last):
(EngineCore pid=1235548) File "/home/user1/.local/share/uv/python/cpython-3.13-linux-x86_64-gnu/lib/python3.13/multiprocessing/process.py", line 313, in _bootstrap
(EngineCore pid=1235548) self.run()
(EngineCore pid=1235548) ~~~~~~~~^^
(EngineCore pid=1235548) File "/home/user1/.local/share/uv/python/cpython-3.13-linux-x86_64-gnu/lib/python3.13/multiprocessing/process.py", line 108, in run
(EngineCore pid=1235548) self._target(*self._args, **self._kwargs)
(EngineCore pid=1235548) ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore pid=1235548) File "/home/user1/vllm-ling-v3/vllm/v1/engine/core.py", line 1353, in run_engine_core
(EngineCore pid=1235548) raise e
(EngineCore pid=1235548) File "/home/user1/vllm-ling-v3/vllm/v1/engine/core.py", line 1318, in run_engine_core
(EngineCore pid=1235548) engine_core = EngineCoreProc(*args, engine_index=dp_rank, **kwargs)
(EngineCore pid=1235548) File "/home/user1/vllm-ling-v3/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore pid=1235548) return func(*args, **kwargs)
(EngineCore pid=1235548) File "/home/user1/vllm-ling-v3/vllm/v1/engine/core.py", line 1074, in __init__
(EngineCore pid=1235548) super().__init__(
(EngineCore pid=1235548) ~~~~~~~~~~~~~~~~^
(EngineCore pid=1235548) vllm_config,
(EngineCore pid=1235548) ^^^^^^^^^^^^
(EngineCore pid=1235548) ...<3 lines>...
(EngineCore pid=1235548) internal_dp_balancing,
(EngineCore pid=1235548) ^^^^^^^^^^^^^^^^^^^^^^
(EngineCore pid=1235548) )
(EngineCore pid=1235548) ^
(EngineCore pid=1235548) File "/home/user1/vllm-ling-v3/vllm/v1/engine/core.py", line 132, in __init__
(EngineCore pid=1235548) self.model_executor = executor_class(vllm_config)
(EngineCore pid=1235548) ~~~~~~~~~~~~~~^^^^^^^^^^^^^
(EngineCore pid=1235548) File "/home/user1/vllm-ling-v3/vllm/v1/executor/multiproc_executor.py", line 108, in __init__
(EngineCore pid=1235548) super().__init__(vllm_config)
(EngineCore pid=1235548) ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^
(EngineCore pid=1235548) File "/home/user1/vllm-ling-v3/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore pid=1235548) return func(*args, **kwargs)
(EngineCore pid=1235548) File "/home/user1/vllm-ling-v3/vllm/v1/executor/abstract.py", line 109, in __init__
(EngineCore pid=1235548) self._init_executor()
(EngineCore pid=1235548) ~~~~~~~~~~~~~~~~~~~^^
(EngineCore pid=1235548) File "/home/user1/vllm-ling-v3/vllm/v1/executor/multiproc_executor.py", line 201, in _init_executor
(EngineCore pid=1235548) self.workers = WorkerProc.wait_for_ready(unready_workers)
(EngineCore pid=1235548) ~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
(EngineCore pid=1235548) File "/home/user1/vllm-ling-v3/vllm/v1/executor/multiproc_executor.py", line 776, in wait_for_ready
(EngineCore pid=1235548) raise e from None
(EngineCore pid=1235548) Exception: WorkerProc initialization failed due to an exception in a background process. See stack trace for root cause.
(APIServer pid=1235284) INFO 08-19 12:28:32 [utils.py:612] [shutdown] Process manager: send sigterm to process EngineCore
(APIServer pid=1235284) Traceback (most recent call last):
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/.venv/bin/vllm", line 10, in <module>
(APIServer pid=1235284) sys.exit(main())
(APIServer pid=1235284) ~~~~^^
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/entrypoints/cli/main.py", line 97, in main
(APIServer pid=1235284) args.dispatch_function(args)
(APIServer pid=1235284) ~~~~~~~~~~~~~~~~~~~~~~^^^^^^
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/entrypoints/cli/serve.py", line 152, in cmd
(APIServer pid=1235284) uvloop.run(run_server(args))
(APIServer pid=1235284) ~~~~~~~~~~^^^^^^^^^^^^^^^^^^
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/.venv/lib/python3.13/site-packages/uvloop/__init__.py", line 96, in run
(APIServer pid=1235284) return __asyncio.run(
(APIServer pid=1235284) ~~~~~~~~~~~~~^
(APIServer pid=1235284) wrapper(),
(APIServer pid=1235284) ^^^^^^^^^^
(APIServer pid=1235284) ...<2 lines>...
(APIServer pid=1235284) **run_kwargs
(APIServer pid=1235284) ^^^^^^^^^^^^
(APIServer pid=1235284) )
(APIServer pid=1235284) ^
(APIServer pid=1235284) File "/home/user1/.local/share/uv/python/cpython-3.13-linux-x86_64-gnu/lib/python3.13/asyncio/runners.py", line 195, in run
(APIServer pid=1235284) return runner.run(main)
(APIServer pid=1235284) ~~~~~~~~~~^^^^^^
(APIServer pid=1235284) File "/home/user1/.local/share/uv/python/cpython-3.13-linux-x86_64-gnu/lib/python3.13/asyncio/runners.py", line 118, in run
(APIServer pid=1235284) return self._loop.run_until_complete(task)
(APIServer pid=1235284) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^
(APIServer pid=1235284) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/.venv/lib/python3.13/site-packages/uvloop/__init__.py", line 48, in wrapper
(APIServer pid=1235284) return await main
(APIServer pid=1235284) ^^^^^^^^^^
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/entrypoints/openai/api_server.py", line 764, in run_server
(APIServer pid=1235284) await run_server_worker(listen_address, sock, args, **uvicorn_kwargs)
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/entrypoints/openai/api_server.py", line 778, in run_server_worker
(APIServer pid=1235284) async with build_async_engine_client(
(APIServer pid=1235284) ~~~~~~~~~~~~~~~~~~~~~~~~~^
(APIServer pid=1235284) args,
(APIServer pid=1235284) ^^^^^
(APIServer pid=1235284) client_config=client_config,
(APIServer pid=1235284) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1235284) ) as engine_client:
(APIServer pid=1235284) ^
(APIServer pid=1235284) File "/home/user1/.local/share/uv/python/cpython-3.13-linux-x86_64-gnu/lib/python3.13/contextlib.py", line 214, in __aenter__
(APIServer pid=1235284) return await anext(self.gen)
(APIServer pid=1235284) ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/entrypoints/openai/api_server.py", line 132, in build_async_engine_client
(APIServer pid=1235284) async with build_async_engine_client_from_engine_args(
(APIServer pid=1235284) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
(APIServer pid=1235284) engine_args,
(APIServer pid=1235284) ^^^^^^^^^^^^
(APIServer pid=1235284) usage_context=usage_context,
(APIServer pid=1235284) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1235284) client_config=client_config,
(APIServer pid=1235284) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1235284) ) as engine:
(APIServer pid=1235284) ^
(APIServer pid=1235284) File "/home/user1/.local/share/uv/python/cpython-3.13-linux-x86_64-gnu/lib/python3.13/contextlib.py", line 214, in __aenter__
(APIServer pid=1235284) return await anext(self.gen)
(APIServer pid=1235284) ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/entrypoints/openai/api_server.py", line 168, in build_async_engine_client_from_engine_args
(APIServer pid=1235284) async_llm = AsyncLLM.from_vllm_config(
(APIServer pid=1235284) vllm_config=vllm_config,
(APIServer pid=1235284) ...<6 lines>...
(APIServer pid=1235284) client_index=client_index,
(APIServer pid=1235284) )
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/v1/engine/async_llm.py", line 220, in from_vllm_config
(APIServer pid=1235284) return cls(
(APIServer pid=1235284) vllm_config=vllm_config,
(APIServer pid=1235284) ...<9 lines>...
(APIServer pid=1235284) client_index=client_index,
(APIServer pid=1235284) )
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/v1/engine/async_llm.py", line 149, in __init__
(APIServer pid=1235284) self.engine_core = EngineCoreClient.make_async_mp_client(
(APIServer pid=1235284) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
(APIServer pid=1235284) vllm_config=vllm_config,
(APIServer pid=1235284) ^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1235284) ...<4 lines>...
(APIServer pid=1235284) client_index=client_index,
(APIServer pid=1235284) ^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1235284) )
(APIServer pid=1235284) ^
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/tracing/otel.py", line 178, in sync_wrapper
(APIServer pid=1235284) return func(*args, **kwargs)
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/v1/engine/core_client.py", line 139, in make_async_mp_client
(APIServer pid=1235284) return AsyncMPClient(*client_args)
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/tracing/otel.py", line 178, in sync_wrapper
(APIServer pid=1235284) return func(*args, **kwargs)
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/v1/engine/core_client.py", line 987, in __init__
(APIServer pid=1235284) super().__init__(
(APIServer pid=1235284) ~~~~~~~~~~~~~~~~^
(APIServer pid=1235284) asyncio_mode=True,
(APIServer pid=1235284) ^^^^^^^^^^^^^^^^^^
(APIServer pid=1235284) ...<3 lines>...
(APIServer pid=1235284) client_addresses=client_addresses,
(APIServer pid=1235284) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1235284) )
(APIServer pid=1235284) ^
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/v1/engine/core_client.py", line 609, in __init__
(APIServer pid=1235284) with launch_core_engines(
(APIServer pid=1235284) ~~~~~~~~~~~~~~~~~~~^
(APIServer pid=1235284) vllm_config, executor_class, log_stats, addresses
(APIServer pid=1235284) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1235284) ) as (engine_manager, coordinator, addresses, tensor_queue):
(APIServer pid=1235284) ^
(APIServer pid=1235284) File "/home/user1/.local/share/uv/python/cpython-3.13-linux-x86_64-gnu/lib/python3.13/contextlib.py", line 148, in __exit__
(APIServer pid=1235284) next(self.gen)
(APIServer pid=1235284) ~~~~^^^^^^^^^^
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/v1/engine/utils.py", line 1194, in launch_core_engines
(APIServer pid=1235284) wait_for_engine_startup(
(APIServer pid=1235284) ~~~~~~~~~~~~~~~~~~~~~~~^
(APIServer pid=1235284) handshake_socket,
(APIServer pid=1235284) ^^^^^^^^^^^^^^^^^
(APIServer pid=1235284) ...<6 lines>...
(APIServer pid=1235284) coordinator.proc if coordinator else None,
(APIServer pid=1235284) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1235284) )
(APIServer pid=1235284) ^
(APIServer pid=1235284) File "/home/user1/vllm-ling-v3/vllm/v1/engine/utils.py", line 1253, in wait_for_engine_startup
(APIServer pid=1235284) raise RuntimeError(
(APIServer pid=1235284) ...<3 lines>...
(APIServer pid=1235284) )
(APIServer pid=1235284) RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {}