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

Revert "【FIX】Change the name of sparse attn from moba to plas (#3845)" (#4001)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
This reverts commit e31c8f7336.
This commit is contained in:
Jiang-Jia-Jun
2025-09-09 11:08:23 +08:00
committed by GitHub
parent bbd548ceb6
commit c60adf4281
13 changed files with 150 additions and 150 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
fastdeploy/worker/worker_process.py
View File

@@ -34,9 +34,9 @@ from fastdeploy.config import (
FDConfig,
GraphOptimizationConfig,
LoadConfig,
MobaAttentionConfig,
ModelConfig,
ParallelConfig,
PlasAttentionConfig,
SpeculativeConfig,
)
from fastdeploy.input.ernie4_5_tokenizer import Ernie4_5Tokenizer
@@ -561,10 +561,10 @@ def parse_args():
help="Configuration of Graph optimization backend.",
)
parser.add_argument(
"--plas_attention_config",
"--moba_attention_config",
type=json.loads,
default=None,
help="Configation of plas attention.",
help="Configation of moba attention.",
)
parser.add_argument(
"--guided_decoding_backend",
@@ -677,7 +677,7 @@ def initialize_fd_config(args, ranks: int = 1, local_rank: int = 0) -> FDConfig:
graph_opt_config = GraphOptimizationConfig(args.graph_optimization_config)
plas_attention_config = PlasAttentionConfig(args.plas_attention_config)
moba_attention_config = MobaAttentionConfig(args.moba_attention_config)
early_stop_config = EarlyStopConfig(args.early_stop_config)
@@ -777,7 +777,7 @@ def initialize_fd_config(args, ranks: int = 1, local_rank: int = 0) -> FDConfig:
cache_config=cache_config,
engine_worker_queue_port=args.engine_worker_queue_port,
ips=args.ips,
plas_attention_config=plas_attention_config,
moba_attention_config=moba_attention_config,
)
update_fd_config_for_mm(fd_config)