## Dynamic Model in TVM ## AWS AI Presenter: Haichen Shen, Yao Wang Amazon SageMaker Neo, Deep Engine Science ## Models with dynamism • Control flow (if, loop, etc) • Dynamic shapes ☐ Dynamic inputs: loop Limitation of TVM/graph runtime • Cannot compile and run dynamic models ## Support dynamic model in TVM • Support Any-dim in typing • Use shape function to compute the type at runtime • Virtual "data" input_shape = [tvm.relay.Any(), 3, 224, 224] dtype = "float32" block = get_model('resnet50_v1', pretrained=True) mod, params = relay.frontend.from_mxnet(block, shape={input_name:

China 2018 ## Model and Operate Datacenter by Kubernetes at eBay 辛肖刚, Cloud Engineering Manager, ebay 梅岑恺, Senior Operation Manager, ebay ## Agenda About ebay Our fleet ★ Kubernetes makes magic at at ebay Model + Controller How we model our datacenter Operation in large scale Q&A 177M Active buyers worldwide $22.7B Amount of eBay Inc. GMV $2.6B Reported revenue 1.1B Live listings • Network ## Kubernetes • Core components • Addon • Taint ## Operations ## Let's model a datacenter running Kubernetes Onboard ![Image](/uploads/documents/2/4/9/8/249845b422d764ccc2a2fa576344083d/p13_2

## Microsoft Ready ## The Future of Cloud Native Applications with Open Application Model (OAM) and Dapr Mark Russinovich Chief Technology Officer, Microsoft Azure @markrussinovich ## Application models /9/bc29b5fbf1de02f8968a900b84d384e5/p4_1.jpg) Open Application Model (OAM) Open Application Model Platform agnostic application model Distributed Application Runtime (Dapr) dapr Building blocks developing cloud and edge applications Microsoft is introducing two new specs, the Open Application Model and Dapr, with the aim of making building cloud, edge and Kubernetes apps easier. ### f in ☐ ☑ ☒

## +23 ## Distributed Ranges: A Model for Building Distributed Data Structures, Algorithms, and Views ## BENJAMIN BROCK ## Notices and Disclaimers For notices, disclaimers, and details about performance

## +23 ## C++ Memory Model: from C++11 to C++23 ## ALEX DATHSKOVSKY ## 20 23 October 01 - 06 ## About Me: SPEEDATA alex.dathskovsky@speedata.io www.linkedin.com/in/alexdathskovsky https://www.cppnext [Image](/uploads/documents/a/b/8/f/ab8f331d7156e1b708cb39698c0a1f00/p3_1.jpg) ## its a conspiracy man ## Memory Model ## I mportant Question ## Does the processor executes the program you wrote? ## The Answer ## Short It will run what you have intended but: • Compilers reorder and change operations • CPU’s use threading and OOO execution ## Compiler Optimisations ## I f you were the compiler, what would you do? ##

Efficient Mixture-of-Experts Language Model DeepSeek-AI research@deepseek.com ## Abstract We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training DeepSeek-V2 and its chat versions still achieve top-tier performance among open-source models. The model checkpoints are available at https://github.com/deepseek-ai/DeepSeek-V2. ![Image](/uploads/docum A Contributions and Acknowledgments 27 B DeepSeek-V2-Lite: A 16B Model Equipped with MLA and DeepSeekMoE 29 B.1 Model Description ..... 29 B.2 Performance Evaluation ..... 30 C Full Formulas

provides view (e.g. NSView) - Host requests view (e.g. NSView) - We create an OS window ## Threading model - Hosts can call us from any thread Each host may do this differently ![Image](/uploads/do

29 Parallel Computing ..... 267 30 Coroutines ..... 269 30.1 Channels ..... 269 31 Multi-Threading (Experimental) 273 31.1 Setup 273 31.2 The @threads Macro 273 31.3 Atomic Operations 274 and permutation 688 55.7 Array functions 701 55.8 Combinatorics 710 56 Tasks 715 57 Multi-Threading 723 57.1 ccall using a threadpool (Experimental) 728 57.2 Synchronization Primitives 728 58 inbounds 1169 The bounds checking call hierarchy 1169 101.17 Proper maintenance and care of multi-threading locks 1170 Locks 1170 Broken Locks 1171 Shared Global Data Structures 1172 101.18 Arrays

Communicating with Channels 251 23.3 More task operations 254 23.4 Tasks and events 255 24 Multi-Threading 256 24.1 Starting Julia with multiple threads 256 24.2 Data-race freedom 257 24.3 The @threads 48 Tasks 755 48.1 Scheduling 759 48.2 Synchronization 760 48.3 Channels 763 49 Multi-Threading 768 49.1 Synchronization 769 49.2 Atomic operations 770 49.3 ccall using a threadpool (Experimental) runtime ..... 1265 98.16 Bounds checking ..... 1266 98.17 Proper maintenance and care of multi-threading locks ..... 1268 98.18 Arrays with custom indices ..... 1271 98.19 Module loading ..... 1274