Update README.md
Browse files
README.md
CHANGED
|
@@ -71,7 +71,7 @@ The integration of foundation and fine-tuned models into AI systems requires add
|
|
| 71 |
**Usage**
|
| 72 |
* See [Cosmos-Drive-Dreams](https://github.com/nv-tlabs/Cosmos-Drive-Dreams/blob/main/cosmos-transfer-lidargen/examples/lidar_diffusion.md) for inference details
|
| 73 |
|
| 74 |
-
Note: We have only tested doing inference with BF16 precision.
|
| 75 |
|
| 76 |
## Model Version(s):
|
| 77 |
Cosmos LidarGen
|
|
|
|
| 71 |
**Usage**
|
| 72 |
* See [Cosmos-Drive-Dreams](https://github.com/nv-tlabs/Cosmos-Drive-Dreams/blob/main/cosmos-transfer-lidargen/examples/lidar_diffusion.md) for inference details
|
| 73 |
|
| 74 |
+
Note: We have only tested doing inference with BF16 precision. On a single NVIDIA A100-SXM4-80GB GPU, our diffusion model takes around 160 seconds to generate a single Lidar range map from multi-view images.
|
| 75 |
|
| 76 |
## Model Version(s):
|
| 77 |
Cosmos LidarGen
|