Skip to content

Commit

Permalink
#8764: Add disclaimer that current WH models are only on N300 and fix…
Browse files Browse the repository at this point in the history
… installing link in docs
  • Loading branch information
tt-rkim committed May 31, 2024
1 parent 9c22a20 commit 0cc4d15
Show file tree
Hide file tree
Showing 2 changed files with 6 additions and 2 deletions.
6 changes: 5 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,10 @@

## Wormhole (WH) Models

> [!NOTE]
>
> We currently test our demo models for Wormhole on N300 boards only.
| Model | Gen. Token [3] | Batch | End-to-end throughput [1] | Device throughput [2] | Target |
|-------------------------------------------------------------|--------------------|----------------------|------------------------------|-----------------------------|----------------|
| [Falcon7B-decode](./models/demos/wormhole/falcon7b) | 129th | 32 | 11.6 t/s/u - 371 t/s | 15.4 t/s/u - 493 t/s | 21 t/s/u |
Expand All @@ -46,7 +50,7 @@
| [BERT-Large](./models/demos/metal_BERT_large_11/) (sen/s) | any | 8 | 270 | 340 | 400 |
| Stable Diffusion 1.4 512x512 | coming soon | 1 | | | |

[3] - Generating the i'th token in a sequence while the kv_cache is filled with i-1 rows.
[3] - Generating the `i`'th token in a sequence while the kv_cache is filled with `i-1` rows.

## T3000 (2x4 mesh of WHs) Models

Expand Down
2 changes: 1 addition & 1 deletion docs/source/tt-metalium/get_started/get_started.rst
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ hardware.

Install tt-metal and build the project by following the instructions in the
`installation guide
<https://github.com/tenstorrent/tt-metal#installing>`_.
<https://github.com/tenstorrent/tt-metal/blob/main/INSTALLING.md>`_.

2. Explore the Falcon 7B Demo
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Expand Down

0 comments on commit 0cc4d15

Please sign in to comment.