Andrei Panferov e3fc90ae68 Cleaner Cache dtype and device extraction for CUDA graph generation for quantizers compatibility (#29079) ...

* input_layernorm as the beacon of hope

* cleaner dtype extraction

* AQLM + CUDA graph test

* is available check

* shorter text test

2024-02-27 09:32:39 +01:00

..

__init__.py

AQLM quantizer support (#28928)

2024-02-14 09:25:41 +01:00

test_aqlm.py

Cleaner Cache dtype and device extraction for CUDA graph generation for quantizers compatibility (#29079)

2024-02-27 09:32:39 +01:00