apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature] Support using prefix-caching + cudagraph for inference (#2924)

Browse Source 
* fix the bug in cudagraph+prefix-caching but still have some bug with profile

Change-Id: Ibf2ba3f2e3b08641d03f4b1391d7c862c3efa397

* add the signal to make sure cache manager launched

* fix judge condition

* reomove useless control

* update control stream

* update

* fix xpu

* change the do_profile flag

* update

* add new threads to init cache_manager

---------

Co-authored-by: RAM <gstian5555@outlook.com>
This commit is contained in:
Zero Rains
2025-07-22 15:59:45 +08:00
committed by GitHub
parent 48e6a0ca26
commit 89a485b69f
11 changed files with 63 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/engine/args_utils.py
View File

@@ -863,8 +863,6 @@ class EngineArgs:
graph_opt_cfg = self.create_graph_optimization_config()
graph_opt_cfg.update_use_cudagraph(self.use_cudagraph)
assert not (self.use_cudagraph and self.enable_prefix_caching), "Prefix caching cannot be used with CUDA graph"
assert not (
self.tensor_parallel_size <= 1 and self.enable_custom_all_reduce
), "enable_custom_all_reduce must be used with tensor_parallel_size>1"