apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[FDConfig]Remove max_num_batched_tokens/max_num_seqs in parallel config (#4116)

Browse Source 
* remove max_num_batched_tokens in parallel config

* remove max_num_seqs

* update test case

* fix test

* fix

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
YuanRisheng
2025-09-17 10:43:35 +08:00
committed by GitHub
parent c01a756912
commit 2e9e53ff7e
30 changed files with 169 additions and 131 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
fastdeploy/worker/worker_process.py
View File

@@ -44,6 +44,7 @@ from fastdeploy.inter_communicator import EngineWorkerQueue as TaskQueue
from fastdeploy.inter_communicator import IPCSignal
from fastdeploy.model_executor.layers.quantization import parse_quant_config
from fastdeploy.platforms import current_platform
from fastdeploy.scheduler import SchedulerConfig
from fastdeploy.utils import get_logger
from fastdeploy.worker.worker_base import WorkerBase
@@ -662,6 +663,7 @@ def initialize_fd_config(args, ranks: int = 1, local_rank: int = 0) -> FDConfig:
speculative_config = SpeculativeConfig(args.speculative_config)
parallel_config = ParallelConfig(vars(args))
cache_config = CacheConfig(vars(args))
scheduler_config = SchedulerConfig(vars(args))
parallel_config.tensor_parallel_rank = local_rank % parallel_config.tensor_parallel_size
parallel_config.data_parallel_rank = local_rank // parallel_config.tensor_parallel_size
# config for EP
@@ -758,6 +760,7 @@ def initialize_fd_config(args, ranks: int = 1, local_rank: int = 0) -> FDConfig:
graph_opt_config=graph_opt_config,
early_stop_config=early_stop_config,
cache_config=cache_config,
scheduler_config=scheduler_config,
engine_worker_queue_port=args.engine_worker_queue_port,
ips=args.ips,
moba_attention_config=moba_attention_config,