Daniël de Kok 628d6a13da Add support for exl2 quantization ... Mostly straightforward, changes to existing code: * Wrap quantizer parameters in a small wrapper to avoid passing around untyped tuples and needing to repack them as a dict. * Move scratch space computation to warmup, because we need the maximum input sequence length to avoid allocating huge scratch buffers that OOM.		2024-09-24 03:19:39 +00:00
..
env_runtime.rs	Integrate flash attention for starcoder2 tgi through habana and some fixes, enabling (#198)	2024-08-07 22:06:05 +02:00
main.rs	Add support for exl2 quantization	2024-09-24 03:19:39 +00:00