Skip to content

Commit

Permalink
BFLOAT Correction
Browse files Browse the repository at this point in the history
Fixed instances of "BF16" to read "BFLOAT16"
  • Loading branch information
dsklavos committed Jan 7, 2025
1 parent 5ddb5c5 commit cc37ee1
Show file tree
Hide file tree
Showing 2 changed files with 9 additions and 9 deletions.
2 changes: 1 addition & 1 deletion core/aibs/grayskull/specifications.md
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@ The e75/e150 support the following data precision formats:

| Format | Bit Depth |
| -------------------- | ---------------------------- |
| Floating point | FP8, FP16, BF16 |
| Floating point | FP8, FP16, BFLOAT16 |
| Block floating point | BLOCKFP2, BLOCKFP4, BLOCKFP8 |
| Vector | VTF19 |

Expand Down
16 changes: 8 additions & 8 deletions core/aibs/wormhole/specifications.md
Original file line number Diff line number Diff line change
Expand Up @@ -54,14 +54,14 @@ The two QSFP-DD ports are active and support 400GbE connectivity between cards a

The n150/n300 support the following data precision formats:

| Format | Bit Depth |
| -------------------- | --------------------------------------- |
| Floating point | FP8, FP16, BF16<br />FP32 (Output Only) |
| Block floating point | BLOCKFP2, BLOCKFP4, BLOCKFP8 |
| Integer | INT8<br />INT32 (Output Only) |
| Unsigned Integer | UINT8 |
| TensorFloat | TF32 |
| Vector | VTF19, VFP32 |
| Format | Bit Depth |
| -------------------- | ------------------------------------------- |
| Floating point | FP8, FP16, BFLOAT16<br />FP32 (Output Only) |
| Block floating point | BLOCKFP2, BLOCKFP4, BLOCKFP8 |
| Integer | INT8<br />INT32 (Output Only) |
| Unsigned Integer | UINT8 |
| TensorFloat | TF32 |
| Vector | VTF19, VFP32 |

## Minimum System Requirements

Expand Down

0 comments on commit cc37ee1

Please sign in to comment.