 AlpinDale
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 months ago |
 AlpinDale
|
5cedee9024
fix gemma with gptq marlin
|
7 months ago |
|
AlpinDale
|
5b0c11d190
support pipeline parallel pynccl groups
|
8 months ago |
|
AlpinDale
|
c66b1b57b1
Marlin 2:4 sparsity (#555)
|
8 months ago |
|
AlpinDale
|
ad1c6b86a1
gptq_marlin: enable bfloat16
|
8 months ago |
|
AlpinDale
|
c154578c97
gptq_marlin: 8bit GPTQ support
|
8 months ago |
|
AlpinDale
|
ac5b4b6aa7
broadcast metadata through cpu
|
8 months ago |
|
AlpinDale
|
f22b700ee4
feat: marlin kernels for GPTQ (#547)
|
8 months ago |
