Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
htyu authored Nov 18, 2024
1 parent 438b64c commit 714a49d
Showing 1 changed file with 3 additions and 2 deletions.
5 changes: 3 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -162,6 +162,7 @@ This pass also lowers `loadOp`s to `AsyncTMACopyGlobalToLocalOp` or `AsyncCopyGl
(8, 16, 8192, 128) 548.783 561.539 482.664
```

Benchmarking instructions:
```
git clone //github.com/pytorch-labs/tritonbench.git
cd tritonbench
Expand All @@ -188,7 +189,7 @@ Without warp specialization:
```


Benchmarking instructions and can be below:
Benchmarking instructions:

```
git clone //github.com/pytorch-labs/tritonbench.git
Expand All @@ -199,7 +200,7 @@ python run.py --op fp8_gemm_rowwise --m 8192 --n 8192 --k 8192 --no_fp8_fast_a
python run.py --op fp8_gemm_rowwise --m 8192 --n 8192 --k 8192 --no_fp8_fast_accum
```

## FP16 GEMM




Expand Down

0 comments on commit 714a49d

Please sign in to comment.