 AlpinDale
|
f2b6dc3872
cpu: add support for W8A8 quantization via compressed-tensor (#1017)
|
4 هفته پیش |
|
AlpinDale
|
9f3e7c86e2
feat: add fused Marlin MoE kernel (#934)
|
1 ماه پیش |
|
AlpinDale
|
5cb2e998d8
quants: update compressed tensors lifecycle to remove `prefix` from `create_weights` (#924)
|
1 ماه پیش |
|
AlpinDale
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
1 ماه پیش |
|
AlpinDale
|
04da8c33bd
Revert "chore: use the `compressed-tensors` library to avoid code reuse (#704)" (#706)
|
4 ماه پیش |
|
AlpinDale
|
f5bbf07c90
chore: use the `compressed-tensors` library to avoid code reuse (#704)
|
4 ماه پیش |
|
AlpinDale
|
f1e1d0bd3d
feat: introduce `BaseAphroditeParameter` (#646)
|
4 ماه پیش |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 ماه پیش |
