[Kernel] Add B12X dense linear backends (#52016)
Signed-off-by: Luke Alonso <lalonso@gmail.com>
This commit is contained in:
@@ -0,0 +1,24 @@
|
||||
# B12X Linear Backend
|
||||
|
||||
[B12X](https://pypi.org/project/b12x/) provides optional CUDA kernels for
|
||||
NVIDIA SM120 and SM121 GPUs. Install the dependency with:
|
||||
|
||||
```bash
|
||||
uv pip install "vllm[b12x]"
|
||||
```
|
||||
|
||||
B12X participates in automatic kernel selection after established optimized
|
||||
backends and before emulation. Select it explicitly with:
|
||||
|
||||
```bash
|
||||
vllm serve <model> --linear-backend b12x
|
||||
```
|
||||
|
||||
## Supported Configurations
|
||||
|
||||
| Backend | Supported configurations |
|
||||
| ------- | ------------------------ |
|
||||
| Linear | Per-tensor FP8, 128x128 block FP8, MXFP8, NVFP4, and MXFP4 |
|
||||
|
||||
Dense W4A16 layers are not handled by B12X and continue to use another
|
||||
compatible backend such as Marlin.
|
||||
Reference in New Issue
Block a user