in TVM ● Support Any-dim in typing ● Use shape function to compute the type at runtime ● Virtual machine as a new runtime for Relay ● Dynamic codegen (WIP) ○ Kernel dispatch for a single op ○ Graph Data dependent© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Relay virtual machine Relay Executable relay.vm.compile Relay Object (hardware independent) Code segment VM Func data type using the entries from a register. AllocClosure Allocates a closure with a lowered virtual machine function. If Jumps to the true or false offset depending on the condition. Goto Unconditionally

Computational PhD in Machine Lesming Phb in Computer Arhiecure oon) PhD in Programming nd Complers Biology and Machine Professor Intel orMicrosof Apple Qualcomm 40+ years of combined experience in computer systems design and machine learning tr tvm 。 @zxnet 和os 全 W Open Source at OctoML ee We are big believers areas: o Core Infrastructure Improvements to TVM o_uTVM: support for microcontrollers in TVM o_ Virtual Machine and dynamic NNs support (w/ AWS folks) o_ Improved NLP support, with focus on transformers QQ

Development Trending = Unprecedented37 Machine-Learning Model* Trending = In 2015... Industry Surpassed Academia as Data + Compute + Financial Needs Rose *Machine Learning = A subset of AI where machines AI, an AI Index data provider, uses the term ‘notable machine learning models’ to designate particularly influential models within the AI/machine learning ecosystem. Epoch maintains a database of 900 Academia Era 2015-today: Industry Era Global Notable Machine Learning Models by Sector – 2003-2024, per Stanford HAI Annual New Notable Machine-Learning Models AI Development Trending = Unprecedented38

(typemin(Float32),typemax(Float32)) (-Inf32, Inf32) julia> (typemin(Float64),typemax(Float64)) (-Inf, Inf) Machine epsilon Most real numbers cannot be represented exactly with floating-point numbers, and so for the distance between two adjacent representable floating-point numbers, which is often known as machine epsilon. Julia provides eps, which gives the distance between 1.0 and the next larger representable antic- ipate. For example, the fib(n::Integer) function above works equally well for Int arguments (machine integers) and BigInt arbitrary-precision integers (see BigFloats and BigInts), which is especially

(typemin(Float32),typemax(Float32)) (-Inf32, Inf32) julia> (typemin(Float64),typemax(Float64)) (-Inf, Inf) Machine epsilon Most real numbers cannot be represented exactly with floating-point numbers, and so for the distance between two adjacent representable floating-point numbers, which is often known as machine epsilon. Julia provides eps, which gives the distance between 1.0 and the next larger representable antic- ipate. For example, the fib(n::Integer) function above works equally well for Int arguments (machine integers) and BigInt arbitrary-precision integers (see BigFloats and BigInts), which is especially

(typemin(Float32),typemax(Float32)) (-Inf32, Inf32) julia> (typemin(Float64),typemax(Float64)) (-Inf, Inf) Machine epsilon Most real numbers cannot be represented exactly with floating-point numbers, and so for the distance between two adjacent representable floating-point numbers, which is often known as machine epsilon. Julia provides eps, which gives the distance between 1.0 and the next larger representable antic- ipate. For example, the fib(n::Integer) function above works equally well for Int arguments (machine integers) and BigInt arbitrary-precision integers (see BigFloats and BigInts), which is especially

(typemin(Float32),typemax(Float32)) (-Inf32, Inf32) julia> (typemin(Float64),typemax(Float64)) (-Inf, Inf) Machine epsilon Most real numbers cannot be represented exactly with floating-point numbers, and so for the distance between two adjacent representable floating-point numbers, which is often known as machine epsilon. Julia provides eps, which gives the distance between 1.0 and the next larger representable antic- ipate. For example, the fib(n::Integer) function above works equally well for Int arguments (machine integers) and BigInt arbitrary-precision integers (see BigFloats and BigInts), which is especially

(typemin(Float32),typemax(Float32)) (-Inf32, Inf32) julia> (typemin(Float64),typemax(Float64)) (-Inf, Inf) Machine epsilon Most real numbers cannot be represented exactly with floating-point numbers, and so for the distance between two adjacent representable floating-point numbers, which is often known as machine epsilon. Julia provides eps, which gives the distance between 1.0 and the next larger representable antic- ipate. For example, the fib(n::Integer) function above works equally well for Int arguments (machine integers) and BigInt arbitrary-precision integers (see BigFloats and BigInts), which is especially

(typemin(Float32),typemax(Float32)) (-Inf32, Inf32) julia> (typemin(Float64),typemax(Float64)) (-Inf, Inf) Machine epsilon Most real numbers cannot be represented exactly with floating-point numbers, and so for the distance between two adjacent representable floating-point numbers, which is often known as machine epsilon. Julia provides eps, which gives the distance between 1.0 and the next larger representable antic- ipate. For example, the fib(n::Integer) function above works equally well for Int arguments (machine integers) and BigInt arbitrary-precision integers (see BigFloats and BigInts), which is especially

(typemin(Float32),typemax(Float32)) (-Inf32, Inf32) julia> (typemin(Float64),typemax(Float64)) (-Inf, Inf) Machine epsilon Most real numbers cannot be represented exactly with floating-point numbers, and so for the distance between two adjacent representable floating-point numbers, which is often known as machine epsilon. Julia provides eps, which gives the distance between 1.0 and the next larger representable antic- ipate. For example, the fib(n::Integer) function above works equally well for Int arguments (machine integers) and BigInt arbitrary-precision integers (see BigFloats and BigInts), which is especially