|
About the compiler category
|
|
0
|
102
|
January 22, 2021
|
|
Where do the 2000+ PyTorch operators come from?: More than you wanted to know
|
|
0
|
111
|
October 12, 2021
|
|
Loop_tool's lazy frontend - Experimenting with symbolic laziness
|
|
0
|
34
|
October 11, 2021
|
|
torch-MLIR presentation from Google / nod.ai
|
|
1
|
71
|
October 8, 2021
|
|
TorchDynamo: An Experiment in Dynamic Python Bytecode Transformation
|
|
0
|
162
|
September 24, 2021
|
|
Next Steps for PyTorch Compilers
|
|
8
|
1587
|
September 8, 2021
|
|
Universal binaries for libtorch Mac?
|
|
7
|
174
|
August 19, 2021
|
|
Where we are headed and why it looks a lot like Julia (but not exactly like Julia)
|
|
0
|
781
|
July 21, 2021
|
|
Python Operator Authoring w/ NNC
|
|
0
|
431
|
June 25, 2021
|
|
Depthwise conv2d: An NNC Case Study
|
|
0
|
222
|
April 7, 2021
|
|
Symbolic Shape Inference
|
|
1
|
189
|
March 31, 2021
|
|
Summary of Issues Found in Adapting Models to use TorchScript
|
|
1
|
171
|
March 16, 2021
|
|
ExecutionPlan caching in ProfilingGraphExecutorImpl?
|
|
0
|
93
|
March 3, 2021
|
|
Prim::autocast_promote operation?
|
|
3
|
143
|
March 2, 2021
|
|
Adapting Models to use TorchScript and Getting them to Produce Fusions
|
|
15
|
614
|
February 26, 2021
|
|
JIT scripting & Autocast
|
|
11
|
499
|
February 23, 2021
|
|
Single-op fusion benchmarking
|
|
0
|
135
|
February 4, 2021
|
|
NNC walkthrough: how PyTorch ops get fused
|
|
0
|
237
|
February 4, 2021
|
|
NNC Per-Operator Benchmarks (on CPU)
|
|
5
|
177
|
January 27, 2021
|
|
Reducing Framework Overhead with Static Runtime
|
|
1
|
301
|
January 27, 2021
|
|
TorchScript usability
|
|
2
|
371
|
January 26, 2021
|
|
Eliminating Framework Overhead by Compiling a Model Directly
|
|
3
|
317
|
January 25, 2021
|
|
Understanding TorchScript Type System
|
|
2
|
265
|
January 25, 2021
|
|
Perf counters for fun and profit
|
|
0
|
144
|
January 23, 2021
|
|
Quick Intro to E-Graphs
|
|
0
|
168
|
January 22, 2021
|
