Pinned
ICYMI, all of the sessions from #tvmcon are available for streaming! Catch up on the latest advances, case studies, and tutorials in #ML acceleration from the @ApacheTVM community. tvmcon.org
Apache TVM
696 posts
Apache TVM
@ApacheTVM
Open deep learning compiler stack for CPUs, GPUs and specialized accelerators.
Join us for the TVM and Deep Learning Compilation Conference tvmcon.org
Joined January 2018
- Introducing @PyTorch 's TVM-based backend by Bram Wasti (Facebook). seamless integration and great speedups. 🔥🚀🚀tvm.ai/2019/05/30/pyt…
- Compiling Machine Learning to WASM and WebGPU with Apache TVM. Preliminary experiments shows that TVM’s WebGPU backend can get close to native GPU performance when deploying models to the web.🚀🚀 tvm.apache.org/2020/05/14/com…
- Bridging PyTorch and TVM tvm.apache.org/2020/07/14/ber… by @ThomasViehmann talks about using TVM to deploy 🤗 bert on AMD GPUs, and explores the initial path toward training compilation 🐴🐴
- Videos and slides for the 2nd TVM and Deep Learning Compilation Conference are now available! sampl.cs.washington.edu/tvmconf/#about…
- Introducing tvm.ai, the new home for TVM stack, with a mission to bring open, end-to-end deep compiler for cpus, gpus and specialized accelerators.
- Presentation slides for TVM and Deep Learning Compiler Conference are now available. Check out 20+ talks on differentiable programming, quantization, IoT, ASIC, machine learning for systems and more sampl.cs.washington.edu/tvmconf/#about…
- TVM 0.5 is here github.com/dmlc/tvm/relea… High-level differentiable programming Relay IR, flexible low bit quantization flow, better AutoTVM; @golang and @rustlang support; Most importantly, an open, collaborative and growing community!
- Automating Optimization of Quantized Deep Learning Models on CUDA. With learning-based program optimizer. Wuwei Lin is able to get competitive performance on benchmark models and significant boost on emerging models against TensorRT(int8). tvm.ai/2019/04/29/opt…
- Blog: "Automating Generation of Low Precision Deep Learning Operators". Ultra low-bit deep learning operators have the potential to power IoT, but are extremely hard to write and optimize. Meghan from UW SAMPL group shows how to automate this process. tvm.ai/2018/12/18/low…
- Introducing VTA, the open-source, generic, and customizable deep learning accelerator with a complete deep learning software stack, so you can start to experiment with hardware specialization right away with a friendly python interface: tvm.ai/2018/07/12/vta…
- TinyML - How TVM is Taming Tiny -- automate ML optimization for bare-metal devices. tvm.apache.org/2020/06/04/tin… by @DoobsParn Andrew Reusch from @octoml
- TVM Deep Learning Compiler Community Joins Apache Software Foundation @TheASF tvm.ai/2019/03/18/tvm…
