You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit b928496
Browse filesBrowse the repository at this point in the historyBrowse files
Copy file name to clipboardExpand all lines: examples/models/voxtral/README.md
+12-6Lines changed: 12 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -89,8 +89,7 @@ optimum-cli export executorch \
89
89
```
90
90
91
91
This will generate:
92
-
-`model.pte` - The exported model
93
-
-`aoti_metal_blob.ptd` - The Metal kernel blob required for runtime
92
+
-`model.pte` - The exported model (includes Metal kernel blob)
94
93
95
94
See the "Building the multimodal runner" section below for instructions on building with Metal support, and the "Running the model" section for runtime instructions.
96
95
@@ -162,10 +161,17 @@ If you already have a preprocessed mel spectrogram saved as a `.bin` file, you c
162
161
--audio_path path/to/preprocessed_audio.bin
163
162
```
164
163
165
-
### Running on CUDA or Metal:
166
-
Add the `--data_path` argument to provide the appropriate data blob to the commands above:
167
-
- For CUDA: `--data_path path/to/aoti_cuda_blob.ptd`
168
-
- For Metal: `--data_path path/to/aoti_metal_blob.ptd`
164
+
### Running on CUDA:
165
+
Add the `--data_path` argument to provide the CUDA data blob:
0 commit comments