apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[SOT] Add sot warmup (NVIDIA GPU Only) (#2929)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* add sot warmup

* fix code style

* change batch_size list

* add param to config

* rm free_list settings && set sot_warmup_sizes

* finish debug with dynamic dims by type annotations

* add profile_run guard

* rm sth useless
This commit is contained in:
Ryan
2025-07-22 21:36:14 +08:00
committed by GitHub
parent 7c5e34e72d
commit 95b5af24db
7 changed files with 71 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
fastdeploy/worker/worker_process.py
View File

@@ -632,6 +632,7 @@ def initialize_fd_config(args, ranks: int = 1, local_rank: int = 0) -> FDConfig:
use_cudagraph=args.graph_optimization_config["use_cudagraph"],
graph_opt_level=args.graph_optimization_config["graph_opt_level"],
cudagraph_capture_sizes=args.graph_optimization_config["cudagraph_capture_sizes"],
sot_warmup_sizes=args.graph_optimization_config["sot_warmup_sizes"],
)
# Note(tangbinhan): used for load_checkpoint