3 Commits

Author	SHA1	Message	Date
OlivierDehaene	53ec0b790b	feat(fp8): use fbgemm kernels and load fp8 weights directly (#2248) ... * feat(fp8): add support for fbgemm * allow loading fp8 weights directly * update outlines * fix makefile * build fbgemm * avoid circular import and fix dockerfile * add default dtype * refactored weights loader * fix auto conversion * fix quantization config parsing * force new nccl on install * missing get_weights implementation * increase timeout	2024-07-20 19:02:04 +02:00
OlivierDehaene	630800eed3	v1.3.4	2023-12-22 15:46:04 +01:00
OlivierDehaene	564199bab3	feat: update exllamav2 kernels (#1370) ... Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>	2023-12-21 17:25:22 +01:00