apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-10 02:50:19 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

[XPU] Update XPU L3 Cache setting docs (#2001)

Browse Source 
* [patchelf] fix patchelf error for inference xpu

* [serving] add xpu dockerfile and support fd server

* [serving] add xpu dockerfile and support fd server

* [Serving] support XPU + Tritron

* [Serving] support XPU + Tritron

* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0

* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0

* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0

* [Dockerfile] add comments for xpu tritron dockerfile

* [Doruntime] fix xpu infer error

* [Doruntime] fix xpu infer error

* [XPU] update xpu dockerfile

* add xpu triton server docs

* add xpu triton server docs

* add xpu triton server docs

* add xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* [XPU] Update XPU L3 Cache setting docs
This commit is contained in:
DefTruth
2023-05-30 11:21:04 +08:00
committed by GitHub
parent 434b48dda5
commit 387c5695b3
4 changed files with 14 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
fastdeploy/runtime/backends/paddle/paddle_backend.cc
View File

@@ -84,6 +84,9 @@ void PaddleBackend::BuildOption(const PaddleBackendOption& option) {
#endif
} else if (option.device == Device::KUNLUNXIN) {
#ifdef WITH_KUNLUNXIN
// Note(qiuyanjun): For Paddle XPU L3 Cache, please set
// export XPU_PADDLE_L3_SIZE=67104768 (XPU R200)
// export FLAGS_fuse_multi_transformer_quant_type="float"
config_.EnableXpu(option.xpu_option.kunlunxin_l3_workspace_size,
option.xpu_option.kunlunxin_locked,
option.xpu_option.kunlunxin_autotune,
@@ -117,6 +120,9 @@ void PaddleBackend::BuildOption(const PaddleBackendOption& option) {
} else {
config_.SetCpuMathLibraryNumThreads(option.cpu_thread_num);
}
// Note: SwitchIrOptim is enabled by default for paddle inference
// backend. So, we don't need to set it manually.
// config_.SwitchIrOptim(option.switch_ir_optimize);
}
bool PaddleBackend::Init(const RuntimeOption& runtime_option) {