Félix Marty edfbfdfb3f Merge branch 'main' into gptq-cuda-kernels		2023-07-19 16:58:54 +02:00
..
custom_autotune.py	feat(server): Add inference support for GPTQ (llama + falcon tested) + Quantization script (#438)	2023-06-26 12:27:01 +02:00
quant_linear.py	cleanup	2023-07-12 16:16:58 +00:00
quantize.py	feat(server): Reworking the quantization script so it's still universal (not llama specific) (#587)	2023-07-18 12:19:05 +02:00