63 posts in total

---

2024

11-06

MLIR — Using Tablegen for Passes

10-30

MLIR-Writing Our First Pass

10-28

MLIR-Running and Testing a Lowering

10-23

DistriFusion

10-21

Deepseed Ulysses

10-16

TVM Python/C++ Interaction

10-05

Efficient Large-Scale Language Model Training on GPU Clusters

10-02

Megatron-LM

09-29

PipeFusion-Displaced Patch Pipeline Parallelism for Inference of DiT Models

09-27

xDiT Principle