[CI] Revert PRs 34818 and 33600 (#34979)
This commit is contained in:
@@ -41,7 +41,6 @@ from vllm.distributed.parallel_state import (
|
||||
)
|
||||
from vllm.envs import enable_envs_cache
|
||||
from vllm.logger import init_logger
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.tracing import instrument, maybe_init_worker_tracer
|
||||
from vllm.utils.network_utils import (
|
||||
get_distributed_init_method,
|
||||
@@ -580,9 +579,6 @@ class WorkerProc:
|
||||
self._init_message_queues(input_shm_handle, vllm_config)
|
||||
self.worker.load_model()
|
||||
|
||||
# Set block size based on the attention backends
|
||||
current_platform.update_block_size_for_backend(vllm_config)
|
||||
|
||||
# Enable environment variable cache (e.g. assume no more
|
||||
# environment variable overrides after this point)
|
||||
enable_envs_cache()
|
||||
|
||||
@@ -385,11 +385,6 @@ class RayDistributedExecutor(Executor):
|
||||
self.collective_rpc("init_device")
|
||||
self.collective_rpc("load_model")
|
||||
|
||||
def _update_block_size(worker):
|
||||
current_platform.update_block_size_for_backend(worker.vllm_config)
|
||||
|
||||
self.collective_rpc(_update_block_size)
|
||||
|
||||
for pp_rank in range(self.parallel_config.pipeline_parallel_size):
|
||||
self.pp_tp_workers.append([])
|
||||
for tp_rank in range(self.parallel_config.tensor_parallel_size):
|
||||
|
||||
@@ -12,7 +12,6 @@ import torch.distributed as dist
|
||||
|
||||
import vllm.envs as envs
|
||||
from vllm.logger import init_logger
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.utils.network_utils import get_distributed_init_method, get_ip, get_open_port
|
||||
from vllm.v1.core.sched.output import GrammarOutput, SchedulerOutput
|
||||
from vllm.v1.engine import ReconfigureDistributedRequest, ReconfigureRankType
|
||||
@@ -47,7 +46,6 @@ class UniProcExecutor(Executor):
|
||||
self.driver_worker.init_worker(all_kwargs=[kwargs])
|
||||
self.driver_worker.init_device()
|
||||
self.driver_worker.load_model()
|
||||
current_platform.update_block_size_for_backend(self.vllm_config)
|
||||
|
||||
def _distributed_args(self) -> tuple[str, int, int]:
|
||||
"""Return (distributed_init_method, rank, local_rank)."""
|
||||
|
||||
Reference in New Issue
Block a user