Pinned Repositories
effective_transformer
Running BERT without Padding
architect-awesome
后端架构师技术图谱
architecture.of.internet-product
互联网公司技术架构,微信/淘宝/微博/腾讯/阿里/美团点评/百度/Google/Facebook/Amazon/eBay的架构,欢迎PR补充
ddia
《Designing Data-Intensive Application》DDIA中文翻译
distsys-class
Class materials for a distributed systems lecture series
effective_transformer
Running BERT without Padding
juicefs
JuiceFS is a distributed POSIX file system built on top of Redis and S3.
llama
Inference code for LLaMA models
SDBI
Simple Dynamic Batching Inference
trt_int8_sample
Sample code for nv, int8 seems not work in this case
YellowOldOdd's Repositories
YellowOldOdd/SDBI
Simple Dynamic Batching Inference
YellowOldOdd/architecture.of.internet-product
互联网公司技术架构,微信/淘宝/微博/腾讯/阿里/美团点评/百度/Google/Facebook/Amazon/eBay的架构,欢迎PR补充
YellowOldOdd/distsys-class
Class materials for a distributed systems lecture series
YellowOldOdd/effective_transformer
Running BERT without Padding
YellowOldOdd/trt_int8_sample
Sample code for nv, int8 seems not work in this case
YellowOldOdd/architect-awesome
后端架构师技术图谱
YellowOldOdd/ddia
《Designing Data-Intensive Application》DDIA中文翻译
YellowOldOdd/juicefs
JuiceFS is a distributed POSIX file system built on top of Redis and S3.
YellowOldOdd/llama
Inference code for LLaMA models
YellowOldOdd/MVision
机器人视觉 无人驾驶 视觉SLAM ORB LSD SVO DSO 深度学习目标检测yolov3 行为检测 opencv PCL 双目视觉
YellowOldOdd/onnx-tensorrt
ONNX-TensorRT: TensorRT backend for ONNX
YellowOldOdd/tensorrt-inference-server
The TensorRT Inference Server provides a cloud inferencing solution optimized for NVIDIA GPUs.