From 28a19dbc4e85d3b8a4ec2ef7483bba64d422b43f Mon Sep 17 00:00:00 2001
From: aky15 <ankeyu.aky@11.17.44.249>
Date: 星期三, 12 四月 2023 18:03:06 +0800
Subject: [PATCH] Merge remote-tracking branch 'origin/main' into dev_aky

---
 funasr/export/README.md |   13 ++++++++++++-
 1 files changed, 12 insertions(+), 1 deletions(-)

diff --git a/funasr/export/README.md b/funasr/export/README.md
index bde1e94..97a3de9 100644
--- a/funasr/export/README.md
+++ b/funasr/export/README.md
@@ -17,7 +17,7 @@
        --model-name [model_name] \
        --export-dir [export_dir] \
        --type [onnx, torch] \
-       --quantize \
+       --quantize [true, false] \
        --fallback-num [fallback_num]
    ```
    `model-name`: the model is to export. It could be the models from modelscope, or local finetuned model(named: model.pb).
@@ -30,6 +30,16 @@
 
    `fallback-num`: specify the number of fallback layers to perform automatic mixed precision quantization.
 
+## Performance Benchmark of Runtime
+
+### Paraformer on CPU
+
+[onnx runtime](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/python/benchmark_onnx.md)
+
+[libtorch runtime](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/python/benchmark_libtorch.md)
+
+### Paraformer on GPU
+[nv-triton](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/triton_gpu)
 
 ## For example
 ### Export onnx format model
@@ -55,3 +65,4 @@
 
 ## Acknowledge
 Torch model quantization is supported by [BladeDISC](https://github.com/alibaba/BladeDISC), an end-to-end DynamIc Shape Compiler project for machine learning workloads. BladeDISC provides general, transparent, and ease of use performance optimization for TensorFlow/PyTorch workloads on GPGPU and CPU backends. If you are interested, please contact us.
+

--
Gitblit v1.9.1