|
About the compiler category
|
|
0
|
49
|
January 22, 2021
|
|
Where we are headed and why it looks a lot like Julia (but not exactly like Julia)
|
|
0
|
36
|
July 21, 2021
|
|
Python Operator Authoring w/ NNC
|
|
0
|
118
|
June 25, 2021
|
|
Universal binaries for libtorch Mac?
|
|
3
|
48
|
May 24, 2021
|
|
Depthwise conv2d: An NNC Case Study
|
|
0
|
123
|
April 7, 2021
|
|
Symbolic Shape Inference
|
|
1
|
108
|
March 31, 2021
|
|
Summary of Issues Found in Adapting Models to use TorchScript
|
|
1
|
104
|
March 16, 2021
|
|
ExecutionPlan caching in ProfilingGraphExecutorImpl?
|
|
0
|
54
|
March 3, 2021
|
|
Prim::autocast_promote operation?
|
|
3
|
91
|
March 2, 2021
|
|
Adapting Models to use TorchScript and Getting them to Produce Fusions
|
|
15
|
446
|
February 26, 2021
|
|
JIT scripting & Autocast
|
|
11
|
345
|
February 23, 2021
|
|
Single-op fusion benchmarking
|
|
0
|
89
|
February 4, 2021
|
|
NNC walkthrough: how PyTorch ops get fused
|
|
0
|
136
|
February 4, 2021
|
|
NNC Per-Operator Benchmarks (on CPU)
|
|
5
|
123
|
January 27, 2021
|
|
Reducing Framework Overhead with Static Runtime
|
|
1
|
208
|
January 27, 2021
|
|
TorchScript usability
|
|
2
|
236
|
January 26, 2021
|
|
Eliminating Framework Overhead by Compiling a Model Directly
|
|
3
|
215
|
January 25, 2021
|
|
Understanding TorchScript Type System
|
|
2
|
165
|
January 25, 2021
|
|
Perf counters for fun and profit
|
|
0
|
94
|
January 23, 2021
|
|
Quick Intro to E-Graphs
|
|
0
|
112
|
January 22, 2021
|
