.. |
schemes
|
92cee435e2
rocm: add more quants, fix _scaled_mm call (#1062)
|
преди 1 месец |
__init__.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
преди 5 месеца |
compressed_tensors.py
|
f2b6dc3872
cpu: add support for W8A8 quantization via compressed-tensor (#1017)
|
преди 1 месец |
compressed_tensors_moe.py
|
201db10f02
models: add support for Phi3 MoE
|
преди 1 месец |
utils.py
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
преди 2 месеца |