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

【FIX】Change the name of sparse attn from moba to plas (#4006) (#4076)

Browse Source 
* 【FIX】Change the name of sparse attn from moba to plas (#4006)

* 更新文档

* 【docs】 update readme (#4000)

* 更新文档

* update readme

* update docs

* 【FIX】Change the name of sparse attn from moba to plas (#3845)

* 更新文档

* 更新文档

* 更新文档

* 更新文档

* 修改moba为plas

* code style

* update ci

* code style

* update ci

* code style

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

* fix max_num_seqs

* fix test load attn

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
yangjianfengo1
2025-09-23 10:26:40 +08:00
committed by GitHub
parent 2c34a557f4
commit 4325b737e7
14 changed files with 152 additions and 152 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
fastdeploy/worker/worker_process.py
View File

@@ -35,9 +35,9 @@ from fastdeploy.config import (
FDConfig,
GraphOptimizationConfig,
LoadConfig,
MobaAttentionConfig,
ModelConfig,
ParallelConfig,
PlasAttentionConfig,
SpeculativeConfig,
)
from fastdeploy.input.ernie4_5_tokenizer import Ernie4_5Tokenizer
@@ -577,10 +577,10 @@ def parse_args():
help="Configuration of Graph optimization backend.",
)
parser.add_argument(
"--moba_attention_config",
"--plas_attention_config",
type=json.loads,
default=None,
help="Configuration of moba attention.",
help="Configation of plas attention.",
)
parser.add_argument(
"--guided_decoding_backend",
@@ -723,7 +723,7 @@ def initialize_fd_config(args, ranks: int = 1, local_rank: int = 0) -> FDConfig:
graph_opt_config = GraphOptimizationConfig(args.graph_optimization_config)
moba_attention_config = MobaAttentionConfig(args.moba_attention_config)
plas_attention_config = PlasAttentionConfig(args.plas_attention_config)
early_stop_config = EarlyStopConfig(args.early_stop_config)
@@ -795,7 +795,7 @@ def initialize_fd_config(args, ranks: int = 1, local_rank: int = 0) -> FDConfig:
cache_config=cache_config,
scheduler_config=scheduler_config,
ips=args.ips,
moba_attention_config=moba_attention_config,
plas_attention_config=plas_attention_config,
)
update_fd_config_for_mm(fd_config)