|
About the compiler category
|
|
0
|
84
|
January 22, 2021
|
|
Next Steps for PyTorch Compilers
|
|
8
|
1218
|
September 8, 2021
|
|
Universal binaries for libtorch Mac?
|
|
7
|
134
|
August 19, 2021
|
|
Where we are headed and why it looks a lot like Julia (but not exactly like Julia)
|
|
0
|
723
|
July 21, 2021
|
|
Python Operator Authoring w/ NNC
|
|
0
|
373
|
June 25, 2021
|
|
Depthwise conv2d: An NNC Case Study
|
|
0
|
191
|
April 7, 2021
|
|
Symbolic Shape Inference
|
|
1
|
166
|
March 31, 2021
|
|
Summary of Issues Found in Adapting Models to use TorchScript
|
|
1
|
143
|
March 16, 2021
|
|
ExecutionPlan caching in ProfilingGraphExecutorImpl?
|
|
0
|
78
|
March 3, 2021
|
|
Prim::autocast_promote operation?
|
|
3
|
128
|
March 2, 2021
|
|
Adapting Models to use TorchScript and Getting them to Produce Fusions
|
|
15
|
560
|
February 26, 2021
|
|
JIT scripting & Autocast
|
|
11
|
437
|
February 23, 2021
|
|
Single-op fusion benchmarking
|
|
0
|
119
|
February 4, 2021
|
|
NNC walkthrough: how PyTorch ops get fused
|
|
0
|
197
|
February 4, 2021
|
|
NNC Per-Operator Benchmarks (on CPU)
|
|
5
|
161
|
January 27, 2021
|
|
Reducing Framework Overhead with Static Runtime
|
|
1
|
275
|
January 27, 2021
|
|
TorchScript usability
|
|
2
|
316
|
January 26, 2021
|
|
Eliminating Framework Overhead by Compiling a Model Directly
|
|
3
|
297
|
January 25, 2021
|
|
Understanding TorchScript Type System
|
|
2
|
233
|
January 25, 2021
|
|
Perf counters for fun and profit
|
|
0
|
122
|
January 23, 2021
|
|
Quick Intro to E-Graphs
|
|
0
|
147
|
January 22, 2021
|
