Skip to content
This repository has been archived by the owner on Oct 25, 2024. It is now read-only.

fixed typos #522

Merged
merged 1 commit into from
Oct 23, 2023
Merged

fixed typos #522

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions examples/huggingface/pytorch/text-generation/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@ Performance varies by use, configuration and other factors. See platform configu
</tr>
<tr>
<td>IRQ Balance</td>
<td>Eabled</td>
<td>Enabled</td>
</tr>
<tr>
<td>CPU Model</td>
Expand Down Expand Up @@ -103,7 +103,7 @@ Performance varies by use, configuration and other factors. See platform configu
<td>Enabled</td>
</tr>
<tr>
<td>FrequencyGoverner</td>
<td>FrequencyGovernor</td>
<td>Performance</td>
</tr>
</tbody>
Expand Down
2 changes: 1 addition & 1 deletion examples/huggingface/pytorch/text-generation/deployment/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,7 @@ OMP_NUM_THREADS=<physical cores num> numactl -m <node N> -C <cpu list> python ru
```

### Advanced Inference
Neural Engine also supports weight compression to `fp8_4e3m`, `fp8_5e2m` and `int8` **only when runing bf16 graph**. If you want to try, please add arg `--weight_type`, like:
Neural Engine also supports weight compression to `fp8_4e3m`, `fp8_5e2m` and `int8` **only when running bf16 graph**. If you want to try, please add arg `--weight_type`, like:
```bash
OMP_NUM_THREADS=<physical cores num> numactl -m <node N> -C <cpu list> python run_llm.py --max-new-tokens 32 --input-tokens 32 --batch-size 1 --model_path <path to bf16 engine model> --model <model name> --weight_type=fp8_5e2m
```
Loading