Daniël de Kok 1c84a30fe6 MoE Marlin: support `desc_act` for `groupsize != -1` (#2590) ... This change uses the updated Marlin MoE kernel from vLLM to support MoE with activation sorting and groups.		2024-09-30 19:40:25 +02:00
..
__init__.py	Handle GPTQ-Marlin loading in `GPTQMarlinWeightLoader` (#2300)	2024-07-31 13:08:41 +02:00
fp8.py	Split up `layers.marlin` into several files (#2292)	2024-07-24 16:33:26 +02:00
gptq.py	MoE Marlin: support `desc_act` for `groupsize != -1` (#2590)	2024-09-30 19:40:25 +02:00
marlin.py	feat: add ruff and resolve issue (#2262)	2024-07-26 10:29:09 -04:00
util.py	Split up `layers.marlin` into several files (#2292)	2024-07-24 16:33:26 +02:00